mlsanityData to 14 Oct 2026

Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLM

arXiv 2607.18915 ↗First posted 21 Jul 2026cs.CLcited by 0

On the map: LLM reasoning → Hallucination detection and mitigation

Abstract (arXiv)

With the rapid advancement of large language models (LLMs), modern systems not only possess strong foundational capabilities and extensive knowledge, but can also solve complex problems via long, multi-step reasoning. However, as reasoning traces become longer, LLMs may produce a substantial amount of hallucinated content during the reasoning process, which is often difficult to detect. In this work, we conduct a fine-grained analysis of hallucinations arising in LLM reasoning and find that the reasoning traces are particularly prone to Context-Sensitive Factual Hallucinations: cases where the model actually has the relevant knowledge, yet makes factual errors due to contextual interference during reasoning. To address this issue, we propose Step-level Self-Consistency Group Relative Policy Optimization (SSC-GRPO), which assigns step-level rewards to reasoning traces by computing self-consistency scores of individual steps across multiple rollouts. Compared with prior methods, SSC-GRPO achieves state-of-the-art performance on both mathematical reasoning benchmarks and hallucination leaderboards. Our results offer a new perspective for detecting and mitigating hallucinations in the reasoning process of large language models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning. Builds on 20 of its 36 references that are in the map. First posted on arXiv 21 Jul 2026.

Builds on

20 of 36 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation20 Jun
  2. 2025Are Reasoning Models More Prone to Hallucination?29 May
  3. 2025The Hallucination Tax of Reinforcement Finetuning20 May
  4. 2025Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective19 May
  5. 2024FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning8 Oct

Other references · 15

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2025Qwen3 Technical Reportcited by 8,820
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  8. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  9. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  10. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  11. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 341
  12. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Modelscited by 290
3 more
  1. 2025SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimizationcited by 89
  2. 2025CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Criticcited by 30
  3. 2025TruthRL: Incentivizing Truthful LLMs via Reinforcement Learningcited by 27

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models
  2. 2025Thinking, Faithful and Stable: Mitigating Hallucinations in LLMs
  3. 2025Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification
  4. 2026KDCM: Reducing Hallucination in LLMs through Explicit Reasoning Structures
  5. 2025Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection
  6. 2025Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models
  7. 2025Mitigating Hallucinations in Large Language Models via Causal Reasoning
  8. 2026Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations