mlsanityData to 7 Oct 2026

Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking

arXiv 2501.01306 ↗First posted 2 Jan 2025cs.CLcited by 29

On the map: LLM reasoning → Hallucination detection and mitigation

Abstract (arXiv)

Large language models (LLMs) demonstrate exceptional capabilities, yet still face the hallucination issue. Typical text generation approaches adopt an auto-regressive generation without deliberate reasoning, which often results in untrustworthy and factually inaccurate responses. In this paper, we propose HaluSearch, a novel framework that incorporates tree search-based algorithms (e.g. MCTS) to enable an explicit slow thinking generation process for mitigating hallucinations of LLMs during inference. Specifically, HaluSearch frames text generation as a step-by-step reasoning process, using a self-evaluation reward model to score each generation step and guide the tree search towards the most reliable generation pathway for fully exploiting the internal knowledge of LLMs. To balance efficiency and quality, we introduce a hierarchical thinking system switch mechanism inspired by the dual process theory in cognitive science, which dynamically alternates between fast and slow thinking modes at both the instance and step levels, adapting to the complexity of questions and reasoning states. We conduct extensive experiments on both English and Chinese datasets and the results show that our approach significantly outperforms baseline approaches.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 20 of its 35 references that are in the map. First posted on arXiv 2 Jan 2025.

Builds on

20 of 35 references.

References · 20

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Let's Verify Step by Stepcited by 3,598
  3. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  5. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  6. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 559
  7. 2023A Survey of Hallucination in Large Foundation Modelscited by 365
  8. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 329
  9. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  10. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 230
  11. 2023Fine-tuning Language Models for Factualitycited by 219
  12. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 162
8 more
  1. 2024Distilling System 2 into System 1cited by 152
  2. 2024Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planningcited by 95
  3. 2024LLMs Will Always Hallucinate, and We Need to Live With Thiscited by 77
  4. 2024Enhancing LLM Reasoning with Reward-guided Tree Searchcited by 58
  5. 2024MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Timecited by 40
  6. 2023Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectificationcited by 38
  7. 2024Improving Model Factuality with Fine-grained Critique-based Evaluatorcited by 15
  8. 2024DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 24; 2026: 5.

29 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 131
  3. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 45
  4. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoningcited by 40
  5. 2025Answer Convergence as a Signal for Early Stopping in Reasoningcited by 38
  6. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMscited by 31
  7. 2025The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representationscited by 26
  8. 2025A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Modelscited by 22
  9. 2025Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendationcited by 21
  10. 2025Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoningcited by 21
  11. 2025Towards Concise and Adaptive Thinking in Large Reasoning Models: A Surveycited by 18
  12. 2025KnowRL: Exploring Knowledgeable Reinforcement Learning for Factualitycited by 17
17 more
  1. 2025Generative AI Act II: Test Time Scaling Drives Cognition Engineeringcited by 14
  2. 2025Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safetycited by 10
  3. 2025PATS: Process-Level Adaptive Thinking Mode Switchingcited by 6
  4. 2025On the Provable Performance Guarantee of Efficient Reasoning Modelscited by 6
  5. 2025A Review of Incorporating Psychological Theories in LLMscited by 5
  6. 2025ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Searchcited by 5
  7. 2025VeriDispatcher: Multi-Model Dispatching through Pre-Inference Difficulty Prediction for RTL Generation Optimizationcited by 5
  8. 2025Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generationcited by 4
  9. 2025Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolationcited by 1
  10. 2025Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMscited by 1
  11. 2025From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Modelscited by 1
  12. 2026Anytime Safe PAC Efficient Reasoningcited by 1
  13. 2025Strategic Reflectivism In Intelligent Systemscited by 0
  14. 2026Conditional Performance Guarantee for Large Reasoning Modelscited by 0
  15. 2026Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Modelscited by 0
  16. 2026Building Reliable Long-Form Generation via Hallucination Rejection Samplingcited by 0
  17. 2026MAST: Motif-Augmented Diffusion with Search Tree for Spectroscopic Molecular Structure Elucidationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
  2. 2025Does Less Hallucination Mean Less Creativity? An Empirical Investigation in LLMs
  3. 2026Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
  4. 2025CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation
  5. 2026Can Hallucinations Be Useful? Solving Multi-Hop Questions With SLMs By Chaining System-I/II Reasoning
  6. 2026Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning
  7. 2026Hallucination-Free Automatic Question & Answer Generation for Intuitive Learning
  8. 2025Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems