研究大模型如何随语言身份变化产生类人心理语言反应
From Monolingual to Bilingual: Investigating Language Conditioning in Large Language Models for Psycholinguistic Tasks
- 用双语提示测试模型在不同语言下的心理语言行为
- 中文提示下情绪表征更强更稳定，通义千问更敏感
- 深层网络中心理语言信号更易被探测，适合认知研究
大型语言模型（LLMs）具备强大的语言能力，但其跨语言心理语言知识的编码机制尚不明确。本文通过音义关联和词汇情感两任务，探究 Llama-3.3-70B-Instruct 与 Qwen2.5-72B-Instruct 在英、荷、中三语单语与双语提示下的表现。结果表明，两类模型均能根据提示语言调整输出，其中通义千问对荷语与汉语的区分更敏锐。探针分析显示，心理语言信号在深层网络中更可解码，且中文提示下情绪表征更强且更稳定。研究揭示语言身份会同时影响模型输出行为与内部表征，为模型作为跨语言认知工具提供新洞见。
原文摘要 · Abstract (English)
Large Language Models (LLMs) exhibit strong linguistic capabilities, but little is known about how they encode psycholinguistic knowledge across languages. We investigate whether and how LLMs exhibit human-like psycholinguistic responses under different linguistic identities using two tasks: sound symbolism and word valence. We evaluate two models, Llama-3.3-70B-Instruct and Qwen2.5-72B-Instruct, under monolingual and bilingual prompting in English, Dutch, and Chinese. Behaviorally, both models adjust their outputs based on prompted language identity, with Qwen showing greater sensitivity and sharper distinctions between Dutch and Chinese. Probing analysis reveals that psycholinguistic signals become more decodable in deeper layers, with Chinese prompts yielding stronger and more stable valence representations than Dutch. Our results demonstrate that language identity conditions both output behavior and internal representations in LLMs, providing new insights into their application as models of cross-linguistic cognition.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。