CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
This work addresses the issue of hallucinations in multilingual LLMs for users relying on accurate cross-lingual information, representing an incremental improvement over existing feedback-based abstention strategies.
The paper tackles the problem of knowledge disparities across languages in multilingual LLMs by proposing CausalAbstain, a method that enhances abstention decisions using causal reasoning to select helpful feedback, resulting in improved performance on benchmark datasets for encyclopedic and commonsense QA tasks.
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.