Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases

• URL: http://arxiv.org/abs/2502.14507v1
• Date: Thu, 20 Feb 2025 12:34:46 GMT
• Title: Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases
• Authors: Rena Gao, Xuetong Wu, Tatsuki Kuribayashi, Mingrui Ye, Siya Qi, Carsten Roever, Yuanxing Liu, Zheng Yuan, Jey Han Lau,
• Abstract summary: This study evaluates Large Language Models' ability to simulate non-native-like English use observed in human second language (L2) learners.<n>In dialogue-based interviews, we prompt LLMs to mimic L2 English learners with specific L1s across seven languages.<n>Our analysis examines L1-driven linguistic biases, such as reference word usage and avoidance behaviors, using information-theoretic and distributional density measures.
• Score: 22.048949559200935
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This study evaluates Large Language Models' (LLMs) ability to simulate non-native-like English use observed in human second language (L2) learners interfered with by their native first language (L1). In dialogue-based interviews, we prompt LLMs to mimic L2 English learners with specific L1s (e.g., Japanese, Thai, Urdu) across seven languages, comparing their outputs to real L2 learner data. Our analysis examines L1-driven linguistic biases, such as reference word usage and avoidance behaviors, using information-theoretic and distributional density measures. Results show that modern LLMs (e.g., Qwen2.5, LLAMA3.3, DeepseekV3, GPT-4o) replicate L1-dependent patterns observed in human L2 data, with distinct influences from various languages (e.g., Japanese, Korean, and Mandarin significantly affect tense agreement, and Urdu influences noun-verb collocations). Our results reveal the potential of LLMs for L2 dialogue generation and evaluation for future educational applications.

Related papers

• Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations [72.62400923539234]
  We present the first study to analyze how LLMs recognize knowledge boundaries across different languages. Our empirical studies reveal three key findings: 1) LLMs' perceptions of knowledge boundaries are encoded in the middle to middle-upper layers across different languages.
  arXiv  Detail & Related papers  (2025-04-18T17:44:12Z)
• Multilingual Relative Clause Attachment Ambiguity Resolution in Large Language Models [2.3749120526936465]
  Large language models (LLMs) resolve relative clause (RC) attachment ambiguities. We assess whether LLMs can achieve human-like interpretations amid the complexities of language. We evaluate models in English, Spanish, French, German, Japanese, and Korean.
  arXiv  Detail & Related papers  (2025-03-04T19:56:56Z)
• The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model [59.357993924917]
  We study the evolution of multilingual capabilities in large language models (LLMs) during the pre-training process. We propose the Babel Tower Hypothesis, which describes the entire process of LLMs acquiring new language capabilities. We propose a novel method to construct an optimized pre-training corpus for multilingual code LLMs.
  arXiv  Detail & Related papers  (2024-12-10T08:28:57Z)
• Learning to Write Rationally: How Information Is Distributed in Non-Native Speakers' Essays [1.5039745292757671]
  We compare essays written by second language learners with various native language (L1) backgrounds to investigate how they distribute information in their non-native language (L2) production. Analyses of surprisal and constancy of entropy rate indicated that writers with higher L2 proficiency can reduce the expected uncertainty of language production while still conveying informative content.
  arXiv  Detail & Related papers  (2024-11-05T23:09:37Z)
• Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings [12.507989493130175]
  GPT-4, Llama 2, and Gemini are evaluated for their effectiveness in English compared to other low-resource languages from South Asia. Findings suggest GPT-4 outperformed Llama 2 and Gemini in all five prompt settings and across all languages.
  arXiv  Detail & Related papers  (2024-10-17T02:12:30Z)
• Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models [117.20416338476856]
  Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. We propose a novel detection method, language activation probability entropy (LAPE), to identify language-specific neurons within LLMs. Our findings indicate that LLMs' proficiency in processing a particular language is predominantly due to a small subset of neurons.
  arXiv  Detail & Related papers  (2024-02-26T09:36:05Z)
• Could We Have Had Better Multilingual LLMs If English Was Not the Central Language? [4.655168524016426]
  Large Language Models (LLMs) demonstrate strong machine translation capabilities on languages they are trained on. Our study delves into Llama2's translation capabilities. Our experiments show that the 7B Llama2 model yields above 10 BLEU when translating into all languages it has seen.
  arXiv  Detail & Related papers  (2024-02-21T16:32:38Z)
• Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource Languages [51.301942056881146]
  We investigate how large language models (LLMs) function as rerankers in cross-lingual information retrieval systems for African languages. Our implementation covers English and four African languages (Hausa, Somali, Swahili, and Yoruba) We examine cross-lingual reranking with queries in English and passages in the African languages.
  arXiv  Detail & Related papers  (2023-12-26T18:38:54Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• Second Language Acquisition of Neural Language Models [17.356128991925576]
  This work sheds light on the second language (L2) acquisition of neural language models (LMs) We trained bilingual LMs with a scenario similar to human L2 acquisition and analyzed their cross-lingual transfer from linguistic perspectives.
  arXiv  Detail & Related papers  (2023-06-05T14:32:41Z)
• SLABERT Talk Pretty One Day: Modeling Second Language Acquisition with BERT [0.0]
  Cross-linguistic transfer is the influence of linguistic structure of a speaker's native language on the successful acquisition of a foreign language. We find that NLP literature has not given enough attention to the phenomenon of negative transfer. Our findings call for further research using our novel Transformer-based SLA models.
  arXiv  Detail & Related papers  (2023-05-31T06:22:07Z)
• Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis [103.89753784762445]
  Large language models (LLMs) have demonstrated remarkable potential in handling multilingual machine translation (MMT) This paper systematically investigates the advantages and challenges of LLMs for MMT. We thoroughly evaluate eight popular LLMs, including ChatGPT and GPT-4.
  arXiv  Detail & Related papers  (2023-04-10T15:51:30Z)

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.