走向文化可解释性：一个用于描述和评估大语言模型（LLMs）的语言人类学框架
Toward Cultural Interpretability: A Linguistic Anthropological Framework for Describing and Evaluating Large Language Models (LLMs)
AI总结：
本文提出文化可解释性（CI）框架，融合语言人类学与机器学习，通过分析人机对话，揭示LLM中语言与文化关系，以改善价值对齐，并提出相对性、变异性、索引性三个研究轴。
摘要：
本文提出了一种将语言人类学与机器学习（ML）相结合的新思路，其交汇点在于对语言基础的理解以及使语言技术更具社会责任感这两个方面。语言人类学侧重于解释人类语言使用的文化基础，而机器学习的可解释性领域则致力于揭示大语言模型（LLMs）从人类言语行为中习得的模式。通过分析人类用户与基于LLM的聊天机器人之间的一段对话，我们论证了一个新的联合研究领域——文化可解释性（CI）——在理论上的可行性。通过关注人类用户与AI聊天机器人在人机交互的发音界面中共同生成意义时所涉及的交际能力，CI强调了语言与文化之间的动态关系如何使具有语境敏感性、开放式的对话成为可能。我们认为，通过考察LLMs如何在内部“表征”语言与文化之间的关系，CI能够：（1）为关于这些关系模式化的长期语言人类学问题提供洞见；（2）帮助模型开发者和界面设计者改善语言模型与风格多样的说话者及文化多样的言语社区之间的价值对齐。我们的讨论提出了三个关键研究轴：相对性、变异性和索引性。
英文摘要：
This article proposes a new integration of linguistic anthropology and machine learning (ML) around convergent interests in both the underpinnings of language and making language technologies more socially responsible. While linguistic anthropology focuses on interpreting the cultural basis for human language use, the ML field of interpretability is concerned with uncovering the patterns that Large Language Models (LLMs) learn from human verbal behavior. Through the analysis of a conversation between a human user and an LLM-powered chatbot, we demonstrate the theoretical feasibility of a new, conjoint field of inquiry, cultural interpretability (CI). By focusing attention on the communicative competence involved in the way human users and AI chatbots co-produce meaning in the articulatory interface of human-computer interaction, CI emphasizes how the dynamic relationship between language and culture makes contextually sensitive, open-ended conversation possible. We suggest that, by examining how LLMs internally "represent" relationships between language and culture, CI can: (1) provide insight into long-standing linguistic anthropological questions about the patterning of those relationships; and (2) aid model developers and interface designers in improving value alignment between language models and stylistically diverse speakers and culturally diverse speech communities. Our discussion proposes three critical research axes: relativity, variation, and indexicality.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
