<html aria-label="message body"><head><meta http-equiv="content-type" content="text/html; charset=utf-8"></head><body style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div dir="auto" style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><span style="font-family: Arial, sans-serif; font-size: 12pt; white-space: pre-wrap;">Dear colleagues,</span><br><span id="docs-internal-guid-cf093a9c-7fff-465f-26fe-b92fc96c965e"><br><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">In November 2025, in several LingTyp posts related to large language models (LLMs), I demonstrated how a math-gifted person approaches linguistic problems and explained the basic logic of LLMs. We also searched together for real-world activities that separate form from meaning, which is the case in LLMs. Some LingTyp readers wrote to me that they found this line of inquiry interesting but could not see how LLMs relate to linguistic typology. </span><span style="font-family: Arial, sans-serif; font-size: 12pt; white-space: pre-wrap;">To make this relationship explicit, I would like to initiate a new large-scale scientific experiment with your help. To ensure that this project is robust and impactful, I invite your active participation and expertise.</span></div><br><h3 dir="ltr" style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 14pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Description of the Experiment</span></h3><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">The goal is to task an LLM with providing typological analyses of various language samples covering “neutral” (non-linguistic) topics. We will use:</span></div><ul style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">an English text;</span></div></li><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">a text from another well-studied language (e.g., Russian);</span></div></li><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">a sample from a less-studied language with existing grammars and glossed papers (pre-dating the LLM’s last training cutoff);</span></div></li><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">a sample from a “low-resource” language with only a single grammar and minimal web presence.</span></div></li></ul><br><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">We will analyze these data using four distinct approaches:</span></div><br><ol style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"><li dir="ltr" aria-level="1" style="list-style-type: decimal; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">LLM-style Deep-Network Analysis</span></div></li></ol><div style="line-height: 1.38; margin-left: 36pt; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">An analysis generated by the LLM relying solely on its internal mechanisms—specifically, learned distributional regularities over linear sequences of tokens.</span><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;"><br><br></span></div><ol start="2" style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"><li dir="ltr" aria-level="1" style="list-style-type: decimal; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Descriptive Typological Analysis (WALS-style + Leipzig Glossing Rules)</span></div></li></ol><div style="line-height: 1.38; margin-left: 36pt; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Since modern LLMs (e.g., ChatGPT, Gemini) are trained on vast linguistic texts (including analyses and corpora) and are often fine-tuned for linguistic tasks, they can typically identify languages and apply specific conventions. We will test their ability to gloss raw data and provide WALS-style analyses in varying orders (i.e. first glossing then analysis, and vice versa) to check for consistency.</span><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;"><br><br></span></div><ol start="3" style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"><li dir="ltr" aria-level="1" style="list-style-type: decimal; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Framework-Compatible Analysis</span></div></li></ol><div style="line-height: 1.38; margin-left: 36pt; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">An analysis generated by the LLM within a framework compatible with descriptive typology (e.g., Dependency Grammar or any other well-represented framework online).</span><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;"><br><br></span></div><ol start="4" style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"><li dir="ltr" aria-level="1" style="list-style-type: decimal; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Framework-Incompatible Analysis</span></div></li></ol><div style="line-height: 1.38; margin-left: 36pt; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">An analysis generated by the LLM within a framework not entirely compatible with descriptive typology (e.g., the Minimalist Program, as used in my pilot study).</span></div><br><h3 dir="ltr" style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 14pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Comparison and Conclusions</span></h3><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Finally, we will ask the LLM to compare these four analyses—both language-specifically and cross-linguistically—in order to draw broader typological conclusions.</span></div><br><h3 dir="ltr" style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 14pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">How You Can Help</span></h3><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">To ensure that the experiment is scientifically sound, I am seeking assistance with:</span></div><ul style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Data Selection</span><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">: Identifying appropriate text samples.</span></div></li><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Methodological Rigor</span><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">: Formulating procedures that prevent the model from simply reproducing existing online analyses.</span></div></li><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Expert Evaluation</span><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">: Since LLMs are prone to “hallucinations” or errors, independent expert verification of the outputs is crucial.</span></div></li></ul><br><h3 dir="ltr" style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 14pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Participation and Transparency</span></h3><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; color: rgb(14, 14, 14); font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Once the data sets and the methodology are finalized, I will run the experiment and share the full dialogues with the LLM. However, to ensure replicability, I suggest that each participant also run the experiment independently. I will provide technical guidance to support this and to ensure no-cost research, as well as the use of comparable AI environments. Collaborative execution will allow us to assess the impact of prompt engineering and to determine whether the typological community requires a shared prompt repository.</span></div><br><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">By the conclusion of this project, participants should be able to:</span></div><ul style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">conduct methodologically controlled linguistic analyses using LLMs;</span></div></li><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">ethically reduce research workloads using AI tools;</span></div></li><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">confidently integrate LLMs into linguistics pedagogy.</span></div></li></ul><br><h3 dir="ltr" style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 14pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Proposed Schedule (2026)</span></h3><ul style="margin-top: 0px; margin-bottom: 0px; padding-inline-start: 48px;"><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Data Selection & Methodology</span><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">: End of March</span></div></li><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Experiments & Discussion of Prompts / Individual Results</span><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">: End of April</span></div></li><li dir="ltr" aria-level="1" style="list-style-type: disc; font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre;"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-weight: 700; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Final Results & Takeaways</span><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">: End of June</span><span style="font-size: 12pt; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;"><br><br></span></div></li></ul><h3 dir="ltr" style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 14pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Preliminary Work</span></h3><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">I have already conducted a pilot study using an English text (approx. 1,400 words) generated by Perplexity (to ensure that it was “unseen” by other models) and tested the four types of analysis. </span><span style="font-size: 12pt; font-family: Arial, sans-serif; color: rgb(14, 14, 14); font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">In addition, I used Gemini to produce Quechua sentences and asked ChatGPT to gloss them according to the Leipzig Glossing Rules. I then gave the same glossing task to Gemini. </span><span style="color: rgb(14, 14, 14); font-family: Arial, sans-serif; font-size: 12pt; white-space: pre-wrap;">Interestingly, ChatGPT correctly identified the language, including the specific Quechua variety, and provided a similar, but not identical, analysis to Gemini. </span><span style="color: rgb(14, 14, 14); font-family: Arial, sans-serif; font-size: 12pt; white-space: pre-wrap;">The observed differences were minor and occurred primarily in the translations, without affecting the underlying structural analysis, suggesting overall that the results were not simply copied from a web source but produced by the models.</span></div><br class="Apple-interchange-newline"><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Finally, the strength of this experiment depends on expert deliberation. Although an advanced LLM provides near-instantaneous processing, the substantial work of data selection and qualitative verification requires the time and insight of trained typologists. </span></div><br><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">I look forward to your suggestions for language samples and comments on the proposed methodology, as well as indications of who would be willing to participate in the evaluation phase.</span></div><br><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Kind regards, </span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; font-variant-ligatures: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; vertical-align: baseline; white-space: pre-wrap;">Stela </span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;">—</span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 700; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;">Dr. Stela MANOVA </span><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;"> </span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;">Chief Executive Officer (CEO), MANOVA AI</span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;">Principal Investigator (PI), Gauss:AI Global </span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;">Registration number 655453b</span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;">Sterngasse 3/2/6, 1010 Vienna, Austria</span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;">Email: </span><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;"><span class="Apple-tab-span" style="white-space: pre;"> </span></span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><a href="mailto:manova@manova-ai.com" style="text-decoration: none;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(17, 85, 204); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: underline; text-decoration-skip-ink: none; vertical-align: baseline; white-space: pre-wrap;">manova@manova-ai.com</span></a><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 97, 255); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;"> </span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><a href="mailto:manova@gaussaiglobal.com" style="text-decoration: none;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(17, 85, 204); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: underline; text-decoration-skip-ink: none; vertical-align: baseline; white-space: pre-wrap;">manova@gaussaiglobal.com</span></a><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 97, 255); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;"> </span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><a href="mailto:manova.stela@gmail.com" style="text-decoration: none;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(17, 85, 204); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: underline; text-decoration-skip-ink: none; vertical-align: baseline; white-space: pre-wrap;">manova.stela@gmail.com</span></a><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;"> </span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;">Web: </span><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;"><span class="Apple-tab-span" style="white-space: pre;"> </span></span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><a href="https://www.manova-ai.com/" style="text-decoration: none;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(17, 85, 204); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: underline; text-decoration-skip-ink: none; vertical-align: baseline; white-space: pre-wrap;">https://www.manova-ai.com</span></a></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><a href="https://gaussaiglobal.com/" style="text-decoration: none;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(17, 85, 204); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: underline; text-decoration-skip-ink: none; vertical-align: baseline; white-space: pre-wrap;">https://www.gaussaiglobal.com</span></a></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><a href="https://www.stelamanova.com/" style="text-decoration: none;"><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(17, 85, 204); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: underline; text-decoration-skip-ink: none; vertical-align: baseline; white-space: pre-wrap;">https://www.stelamanova.com</span></a><span style="font-size: 11pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;"> </span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><b id="docs-internal-guid-130576aa-7fff-7aaa-0f99-8a32e1c44baf" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); font-style: normal; font-variant-caps: normal; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration-line: none; text-decoration-thickness: auto; text-decoration-style: solid; font-weight: normal;"><br></b></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: transparent; font-weight: 700; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;">Workshop Series (2026) </span><a href="https://gaussaiglobal.com/LingTransformer/" style="text-decoration: none;"><span style="font-size: 12pt; font-family: Arial, sans-serif; color: rgb(17, 85, 204); background-color: rgb(255, 255, 255); font-weight: 700; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: underline; text-decoration-skip-ink: none; vertical-align: baseline; white-space: pre-wrap;">Linguistics Meets ChatGPT: From Prompt to Theory</span></a></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><span style="font-size: 12pt; font-family: Arial, sans-serif; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255); font-weight: 400; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-variant-alternates: normal; font-variant-numeric: normal; font-variant-east-asian: normal; font-variant-position: normal; font-variant-emoji: normal; text-decoration: none; vertical-align: baseline; white-space: pre-wrap;">Registration for all blocks is now open. Block 1 starts March 23, 2026.</span></div><div style="line-height: 1.38; margin-top: 0pt; margin-bottom: 0pt;"><br></div></span></div></div></div></body></html>