@inproceedings{yang-etal-2026-llm,
title = "{LLM} Agents as Computational Typologists",
author = "Yang, Changbing and
Hammerly, Christopher and
Shi, Freda and
Zhu, Jian",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.514/",
pages = "11790--11815",
ISBN = "979-8-89176-459-0",
abstract = "Linguistic typology relies on expert analysis of reference grammars across languages, making large-scale crosslinguistic comparison labor-intensive and unscalable. We introduce AutoTypologist, an LLM agent for evidence-grounded typological analysis over reference grammars. The agent is capable of retrieving relevant grammar sections, analyzing interlinear glossed text (IGT), and iteratively reasoning over typological hypotheses using a ReAct-style workflow. We evaluate the system on Typological Feature Coding against expert annotations and Typological Hypothesis Testing with typological universals using 25 open-source reference grammars. Operating under different information constraints in Typological Feature Coding, the agent can synthesize information from reference grammar prose but still faces challenges with only IGTs in the target language. In Typological Hypothesis Testing, the agent can synthesize crosslinguistic evidence and identify both supporting cases and counterexamples. These findings suggest that LLM agents can support scalable and inspectable typological analysis, while still requiring expert validation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-llm">
<titleInfo>
<title>LLM Agents as Computational Typologists</title>
</titleInfo>
<name type="personal">
<namePart type="given">Changbing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Hammerly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Freda</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Linguistic typology relies on expert analysis of reference grammars across languages, making large-scale crosslinguistic comparison labor-intensive and unscalable. We introduce AutoTypologist, an LLM agent for evidence-grounded typological analysis over reference grammars. The agent is capable of retrieving relevant grammar sections, analyzing interlinear glossed text (IGT), and iteratively reasoning over typological hypotheses using a ReAct-style workflow. We evaluate the system on Typological Feature Coding against expert annotations and Typological Hypothesis Testing with typological universals using 25 open-source reference grammars. Operating under different information constraints in Typological Feature Coding, the agent can synthesize information from reference grammar prose but still faces challenges with only IGTs in the target language. In Typological Hypothesis Testing, the agent can synthesize crosslinguistic evidence and identify both supporting cases and counterexamples. These findings suggest that LLM agents can support scalable and inspectable typological analysis, while still requiring expert validation.</abstract>
<identifier type="citekey">yang-etal-2026-llm</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.514/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>11790</start>
<end>11815</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM Agents as Computational Typologists
%A Yang, Changbing
%A Hammerly, Christopher
%A Shi, Freda
%A Zhu, Jian
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F yang-etal-2026-llm
%X Linguistic typology relies on expert analysis of reference grammars across languages, making large-scale crosslinguistic comparison labor-intensive and unscalable. We introduce AutoTypologist, an LLM agent for evidence-grounded typological analysis over reference grammars. The agent is capable of retrieving relevant grammar sections, analyzing interlinear glossed text (IGT), and iteratively reasoning over typological hypotheses using a ReAct-style workflow. We evaluate the system on Typological Feature Coding against expert annotations and Typological Hypothesis Testing with typological universals using 25 open-source reference grammars. Operating under different information constraints in Typological Feature Coding, the agent can synthesize information from reference grammar prose but still faces challenges with only IGTs in the target language. In Typological Hypothesis Testing, the agent can synthesize crosslinguistic evidence and identify both supporting cases and counterexamples. These findings suggest that LLM agents can support scalable and inspectable typological analysis, while still requiring expert validation.
%U https://aclanthology.org/2026.emnlp-main.514/
%P 11790-11815
Markdown (Informal)
[LLM Agents as Computational Typologists](https://aclanthology.org/2026.emnlp-main.514/) (Yang et al., EMNLP 2026)
ACL
- Changbing Yang, Christopher Hammerly, Freda Shi, and Jian Zhu. 2026. LLM Agents as Computational Typologists. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 11790–11815, Budapest, Hungary. Association for Computational Linguistics.