LingGym: How Far Are LLMs from Thinking Like Field Linguists?

• URL: http://arxiv.org/abs/2511.00343v1
• Date: Sat, 01 Nov 2025 00:59:13 GMT
• Title: LingGym: How Far Are LLMs from Thinking Like Field Linguists?
• Authors: Changbing Yang, Franklin Ma, Freda Shi, Jian Zhu,
• Abstract summary: This paper introduces LingGym, a new benchmark that evaluates LLMs' capacity for meta-linguistic reasoning.<n>We present a controlled evaluation task: Word-Gloss Inference, in which the model must infer a missing word and gloss from context.<n>Our results show that incorporating structured linguistic cues leads to consistent improvements in reasoning performance across all models.
• Score: 20.482844306874743
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces LingGym, a new benchmark that evaluates LLMs' capacity for meta-linguistic reasoning using Interlinear Glossed Text (IGT) and grammatical descriptions extracted from 18 typologically diverse reference grammars. Unlike previous work that focuses on specific downstream tasks, we assess whether LLMs can generalize linguistic inference across low-resource languages and structures not seen during training. We present a controlled evaluation task: Word-Gloss Inference, in which the model must infer a missing word and gloss from context using varying levels of linguistic information (e.g., glosses, grammatical explanations, translations). Our results show that incorporating structured linguistic cues leads to consistent improvements in reasoning performance across all models. This work highlights both the promise and current limitations of using LLMs for typologically informed linguistic analysis and low-resource language documentation.

Related papers

• CLEAR: A Comprehensive Linguistic Evaluation of Argument Rewriting by Large Language Models [2.872898284494118]
  We focus on argumentative texts and their improvement, a task named Argument Improvement (ArgImp)<n>We present CLEAR: an evaluation pipeline consisting of 57 metrics mapped to four linguistic levels.<n>We find that the models perform ArgImp by shortening the texts while simultaneously increasing average word length and merging sentences.
  arXiv  Detail & Related papers  (2025-09-18T14:53:41Z)
• Self-Correction Makes LLMs Better Parsers [19.20952673157709]
  Large language models (LLMs) have achieved remarkable success across various natural language processing (NLP) tasks.<n>Recent studies suggest that they still face challenges in performing fundamental NLP tasks essential for deep language understanding.<n>We propose a self-correction method that leverages grammar rules from existing treebanks to guide LLMs in correcting previous errors.
  arXiv  Detail & Related papers  (2025-04-19T03:50:59Z)
• Linguistic Blind Spots of Large Language Models [14.755831733659699]
  We study the performance of recent large language models (LLMs) on linguistic annotation tasks.<n>We find that recent LLMs show limited efficacy in addressing linguistic queries and often struggle with linguistically complex inputs.<n>Our results provide insights to inform future advancements in LLM design and development.
  arXiv  Detail & Related papers  (2025-03-25T01:47:13Z)
• Prompt and circumstance: A word-by-word LLM prompting approach to interlinear glossing for low-resource languages [6.4977738682502295]
  We investigate the effectiveness of a retrieval-based LLM prompting approach to glossing, applied to the seven languages from the SIGMORPHON 2023 shared task.<n>Our system beats the BERT-based shared task baseline for every language in the morpheme-level score category.<n>In a case study on Tsez, we ask the LLM to automatically create and follow linguistic instructions, reducing errors on a confusing grammatical feature.
  arXiv  Detail & Related papers  (2025-02-13T21:23:16Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts.<n>We find that Llama Instruct and Mistral models exhibit high degrees of language confusion.<n>We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:03:51Z)
• Holmes: A Benchmark to Assess the Linguistic Competence of Language Models [59.627729608055006]
  We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence. We use computation-based probing to examine LMs' internal representations regarding distinct linguistic phenomena. As a result, we meet recent calls to disentangle LMs' linguistic competence from other cognitive abilities.
  arXiv  Detail & Related papers  (2024-04-29T17:58:36Z)
• PhonologyBench: Evaluating Phonological Skills of Large Language Models [57.80997670335227]
  Phonology, the study of speech's structure and pronunciation rules, is a critical yet often overlooked component in Large Language Model (LLM) research. We present PhonologyBench, a novel benchmark consisting of three diagnostic tasks designed to explicitly test the phonological skills of LLMs. We observe a significant gap of 17% and 45% on Rhyme Word Generation and Syllable counting, respectively, when compared to humans.
  arXiv  Detail & Related papers  (2024-04-03T04:53:14Z)
• Beware of Words: Evaluating the Lexical Diversity of Conversational LLMs using ChatGPT as Case Study [3.0059120458540383]
  We consider the evaluation of the lexical richness of the text generated by conversational Large Language Models (LLMs) and how it depends on the model parameters. The results show how lexical richness depends on the version of ChatGPT and some of its parameters, such as the presence penalty, or on the role assigned to the model.
  arXiv  Detail & Related papers  (2024-02-11T13:41:17Z)
• Native Language Identification with Large Language Models [60.80452362519818]
  We show that GPT models are proficient at NLI classification, with GPT-4 setting a new performance record of 91.7% on the benchmark11 test set in a zero-shot setting. We also show that unlike previous fully-supervised settings, LLMs can perform NLI without being limited to a set of known classes.
  arXiv  Detail & Related papers  (2023-12-13T00:52:15Z)
• Cross-Lingual Knowledge Editing in Large Language Models [73.12622532088564]
  Knowledge editing has been shown to adapt large language models to new knowledge without retraining from scratch. It is still unknown the effect of source language editing on a different target language. We first collect a large-scale cross-lingual synthetic dataset by translating ZsRE from English to Chinese.
  arXiv  Detail & Related papers  (2023-09-16T11:07:52Z)
• Prompting Language Models for Linguistic Structure [73.11488464916668]
  We present a structured prompting approach for linguistic structured prediction tasks. We evaluate this approach on part-of-speech tagging, named entity recognition, and sentence chunking. We find that while PLMs contain significant prior knowledge of task labels due to task leakage into the pretraining corpus, structured prompting can also retrieve linguistic structure with arbitrary labels.
  arXiv  Detail & Related papers  (2022-11-15T01:13:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.