CausalAbstain：利用因果推理增强多语言大语言模型以实现可信赖的弃权（不执行）
CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
AI总结：
本文提出CausalAbstain方法，从因果视角帮助多语言大语言模型选择有用反馈并改进弃权决策，在百科与常识问答基准上优于现有基线。
摘要：
大语言模型（LLMs）在不同语言之间常常表现出知识差异。在多语言场景中，鼓励LLMs在面临知识空白时弃权（不执行）是一种有前景的减少幻觉的策略。当前针对多语言场景的弃权策略主要依赖使用LLMs生成各种语言的反馈并进行自我反思。然而，这些方法可能受到生成反馈中的不准确性和偏见的不利影响。为了解决这一问题，我们从因果视角出发，提出了CausalAbstain方法，该方法帮助LLMs判断是否利用多个生成的反馈响应以及如何识别最有用的响应。大量实验表明，CausalAbstain在母语（Causal-native）和多语言（Causal-multi）设置中均能有效选择有用的反馈，并以可解释性增强弃权决策，在覆盖百科知识和常识知识问答任务的两个基准数据集上优于强基线。我们的代码和数据已在 https://github.com/peachch/CausalAbstain 开源。
英文摘要：
Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to \textit{abstain} when faced with knowledge gaps is a promising strategy to reduce hallucinations in multilingual settings. Current abstention strategies for multilingual scenarios primarily rely on generating feedback in various languages using LLMs and performing self-reflection. However, these methods can be adversely impacted by inaccuracies and biases in the generated feedback. To address this, from a causal perspective, we introduce \textit{CausalAbstain}, a method that helps LLMs determine whether to utilize multiple generated feedback responses and how to identify the most useful ones. Extensive experiments demonstrate that \textit{CausalAbstain} effectively selects helpful feedback and enhances abstention decisions with interpretability in both native language (\textsc{Casual-native}) and multilingual (\textsc{Causal-multi}) settings, outperforming strong baselines on two benchmark datasets covering encyclopedic and commonsense knowledge QA tasks. Our code and data are open-sourced at https://github.com/peachch/CausalAbstain.
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。
