# CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention

arXiv: https://arxiv.org/abs/2506.00519 · HTML: https://mlsanity.com/paper/2506.00519/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 31 May 2025.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning](https://mlsanity.com/paper/2304.05613/) (2023)
- [Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.16039/) (2023)
- [Fine-grained Hallucination Detection and Editing for Language Models](https://mlsanity.com/paper/2401.06855/) (2024)
- [Can Large Language Models Infer Causation from Correlation?](https://mlsanity.com/paper/2306.05836/) (2023)
- [Black-Box Prompt Optimization: Aligning Large Language Models without Model Training](https://mlsanity.com/paper/2311.04155/) (2023)
- [CLadder: Assessing Causal Reasoning in Language Models](https://mlsanity.com/paper/2312.04350/) (2023)
- [Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs](https://mlsanity.com/paper/2305.16339/) (2023)
- [Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering](https://mlsanity.com/paper/2309.17249/) (2023)
- [KoLA: Carefully Benchmarking World Knowledge of Large Language Models](https://mlsanity.com/paper/2306.09296/) (2023)
- [Alignment for Honesty](https://mlsanity.com/paper/2312.07000/) (2023)
- [Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models](https://mlsanity.com/paper/2407.16221/) (2024)
- [Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models](https://mlsanity.com/paper/2305.09955/) (2023)
- [Getting MoRE out of Mixture of Language Model Reasoning Experts](https://mlsanity.com/paper/2305.14628/) (2023)
- [Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals](https://mlsanity.com/paper/2310.00603/) (2023)
- [LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses](https://mlsanity.com/paper/2310.19208/) (2023)
- [Large Language Models and Causal Inference in Collaboration: A Survey](https://mlsanity.com/paper/2403.09606/) (2024)
- [COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective](https://mlsanity.com/paper/2305.05191/) (2023)
- [Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA](https://mlsanity.com/paper/2305.01812/) (2023)
- [Comparing Hallucination Detection Metrics for Multilingual Generation](https://mlsanity.com/paper/2402.10496/) (2024)
- [A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applications](https://mlsanity.com/paper/2404.14809/) (2024)
- [CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision](https://mlsanity.com/paper/2107.09852/) (2021)
- [Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models](https://mlsanity.com/paper/2312.06685/) (2023)
- [LLM4Causal: Democratized Causal Tools for Everyone via Large Language Model](https://mlsanity.com/paper/2312.17122/) (2023)

## Built on by (most cited first, 10 of 10)

- [Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.02993/) (2026)
- [PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models](https://mlsanity.com/paper/2601.10532/) (2026)
- [Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS](https://mlsanity.com/paper/2604.10734/) (2026)
- [RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game](https://mlsanity.com/paper/2604.10740/) (2026)
- [EMSDialog: Synthetic Multi-person Emergency Medical Service Dialogue Generation from Electronic Patient Care Reports via Multi-LLM Agents](https://mlsanity.com/paper/2604.07549/) (2026)
- [REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control](https://mlsanity.com/paper/2511.20233/) (2025)
- [Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms](https://mlsanity.com/paper/2512.15793/) (2025)
- [Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking](https://mlsanity.com/paper/2606.01120/) (2026)
- [Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives](https://mlsanity.com/paper/2604.25423/) (2026)
- [The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining](https://mlsanity.com/paper/2609.32964/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to textitabstain 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 textitCausalAbstain, 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 textitCausalAbstain effectively selects helpful feedback and enhances abstention decisions with interpretability in both native language (textscCasual-native) and multilingual (textscCausal-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.