研究人类与大模型如何在交流中形成共享语言。
Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communication
- 通过参照游戏实验，对比人类、大模型及二者协作时的语言演化
- 无论哪种组合，都能形成可靠沟通的词汇体系，但大模型优化语言更偏离人类习惯
- 人机协作可使语言更贴近人类表达，提示需以沟通成功为训练目标
语言受使用者归纳偏见的影响。我们采用经典的参照游戏，通过人类-人类、大模型-大模型和人类-大模型三类实验，研究在优化人类与大模型归纳偏见条件下，人工语言如何演化。结果表明，在所有情境下均涌现出基于参照的词汇体系，实现可靠沟通，即使人类与大模型协作亦然。条件间比较显示，针对大模型优化的语言与人类优化语言存在细微差异。有趣的是，人类与大模型的互动可缓解这些差异，生成更接近人类语言的词汇体系。本研究深化了对大模型归纳偏见在语言动态演化中作用的理解，有助于维持人机沟通的一致性。尤其强调应探索包含人类交互的新大模型训练方法，并以沟通成功作为奖励信号，这可能成为富有成效的新方向。
原文摘要 · Abstract (English)
Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human, LLM-LLM and Human-LLM experiments. We show that referentially grounded vocabularies emerge that enable reliable communication in all conditions, even when humans \textit{and} LLMs collaborate. Comparisons between conditions reveal that languages optimised for LLMs subtly differ from those optimised for humans. Interestingly, interactions between humans and LLMs alleviate these differences and result in vocabularies more human-like than LLM-like. These findings advance our understanding of the role inductive biases in LLMs play in the dynamic nature of human language and contribute to maintaining alignment in human and machine communication. In particular, our work underscores the need to think of new LLM training methods that include human interaction and shows that using communicative success as a reward signal can be a fruitful, novel direction.
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。