mlsanityData to 7 Oct 2026

CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention

arXiv 2506.00519 ↗First posted 31 May 2025cs.CL cs.AIcited by 10

On the map: LLM reasoning → Causal reasoning in LLMs

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.

Key facts. Cited by 10 papers in the map (data through 7 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.

Builds on

32 of 49 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023CLadder: Assessing Causal Reasoning in Language Models7 Dec
  2. 2023COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective9 May

Other references · 30

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  3. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  4. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  5. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  6. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 518
  7. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  8. 2023ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learningcited by 203
  9. 2023Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedbackcited by 189
  10. 2024Fine-grained Hallucination Detection and Editing for Language Modelscited by 146
  11. 2023Can Large Language Models Infer Causation from Correlation?cited by 142
  12. 2023Black-Box Prompt Optimization: Aligning Large Language Models without Model Trainingcited by 122
18 more
  1. 2023Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMscited by 103
  2. 2023Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineeringcited by 91
  3. 2023KoLA: Carefully Benchmarking World Knowledge of Large Language Modelscited by 85
  4. 2023Alignment for Honestycited by 72
  5. 2024Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Modelscited by 55
  6. 2023Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Modelscited by 46
  7. 2023Getting MoRE out of Mixture of Language Model Reasoning Expertscited by 44
  8. 2023Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactualscited by 44
  9. 2023LitCab: Lightweight Language Model Calibration over Short- and Long-form Responsescited by 44
  10. 2024Large Language Models and Causal Inference in Collaboration: A Surveycited by 26
  11. 2023Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QAcited by 20
  12. 2024Comparing Hallucination Detection Metrics for Multilingual Generationcited by 18
  13. 2024A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applicationscited by 17
  14. 2021CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervisioncited by 12
  15. 2023Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Modelscited by 10
  16. 2023LLM4Causal: Democratized Causal Tools for Everyone via Large Language Modelcited by 9
  17. 2023The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Modelscited by 3
  18. 2018Understanding Back-Translation at Scalecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 8.

10 papers.

  1. 2026Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generationcited by 5
  2. 2026PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Modelscited by 5
  3. 2026Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTScited by 5
  4. 2026RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Gamecited by 3
  5. 2026EMSDialog: Synthetic Multi-person Emergency Medical Service Dialogue Generation from Electronic Patient Care Reports via Multi-LLM Agentscited by 2
  6. 2025REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Controlcited by 1
  7. 2025Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Normscited by 1
  8. 2026Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checkingcited by 1
  9. 2026Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstrativescited by 0
  10. 2026The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstainingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Teaching LLMs to Abstain across Languages via Multilingual Feedback
  2. 2024CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMs
  3. 2025A Survey on Enhancing Causal Reasoning Ability of Large Language Models
  4. 2024A Critical Review of Causal Reasoning Benchmarks for Large Language Models
  5. 2025Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
  6. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causality
  7. 2026METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models
  8. 2026Can Post-Training Transform LLMs into Causal Reasoners?