CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and ApplicationsIEEE Transactions on Knowledge and Data Engineering, 2025
- Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-Modal Language Models2024
- Learning a Structural Causal Model for Intuition Reasoning in ConversationIEEE Transactions on Knowledge and Data Engineering, 2024
- Survey of Hallucination in Natural Language GenerationACM Computing Surveys, 2023
- The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models2023
- Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey2023
- Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA2023
- COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective2023
- Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks2021
- KILT: a Benchmark for Knowledge Intensive Language Tasks2021