mlsanityData to 14 Oct 2026

A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discovery

arXiv 2411.12759 ↗First posted 16 Nov 2024cs.CL cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

The increasing use of large language models (LLMs) in causal discovery as a substitute for human domain experts highlights the need for optimal model selection. This paper presents the first hallucination survey of popular LLMs for causal discovery. We show that hallucinations exist when using LLMs in causal discovery so the choice of LLM is important. We propose using Retrieval Augmented Generation (RAG) to reduce hallucinations when quality data is available. Additionally, we introduce a novel method employing multiple LLMs with an arbiter in a debate to audit edges in causal graphs, achieving a comparable reduction in hallucinations to RAG.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 15 of its 26 references that are in the map. First posted on arXiv 16 Nov 2024.

Builds on

15 of 26 references.

References · 15

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  5. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  6. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  7. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 353
  8. 2021True Few-Shot Learning with Language Modelscited by 344
  9. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 312
  10. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
  11. 2023Sources of Hallucination by Large Language Models on Inference Taskscited by 169
  12. 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 150
3 more
  1. 2023Can large language models build causal graphs?cited by 73
  2. 2023Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluationcited by 69
  3. 2024Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Modelscited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Multi-LLM Collaborative MRI Report Generation for Visual Instruction Tuning in Brain Oncologycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Theoretical Foundations and Mitigation of Hallucination in Large Language Models
  2. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
  3. 2026CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models
  4. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
  5. 2026Unmasking Hallucinations: A Causal Graph-Attention Perspective on Factual Reliability in Large Language Models
  6. 2026Generating Effective CoT Traces for Mitigating Causal Hallucination
  7. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
  8. 2026Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph