Metraipolis › archive › dc_bcfcd3bae854

LLM Agents as Computational Typologists — arXiv:2609.07791

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07791
License (as archived)
CC0-1.0
Archived
2026-10-16T12:45:46.695Z
SHA-256 of the archived text
41e1889613154837e0f30332f56cb6beca024bed4bac5716ed4862458a6dd2ce
Stable URL of this page
https://metraipolis.com/documento/dc_bcfcd3bae854

How to cite

LLM Agents as Computational Typologists — arXiv:2609.07791 — arXiv (en), https://arxiv.org/abs/2609.07791 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcfcd3bae854 (Metraipolis archive dc_bcfcd3bae854, sha256 41e1889613154837e0f30332f56cb6beca024bed4bac5716ed4862458a6dd2ce)
BibTeX
@misc{dcbcfcd3bae854,
  title = {LLM Agents as Computational Typologists — arXiv:2609.07791},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07791},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcfcd3bae854; sha256 41e1889613154837e0f30332f56cb6beca024bed4bac5716ed4862458a6dd2ce},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07791. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.07791 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T12:30:25.143Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).