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

• URL: http://arxiv.org/abs/2607.18915v1
• Date: Tue, 21 Jul 2026 09:56:58 GMT
• Title: Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLM
• Abstract summary: We conduct a fine-grained analysis of hallucinations arising in large language models (LLMs)<n>We find that reasoning traces are particularly prone to Context-Sensitive Factual Hallucinations.<n>We propose Step-level Self-Consistency Group Relative Policy Optimization (SSC-GRPO), which assigns step-level rewards to reasoning traces.
• Score: 20.624980796952112
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models [65.97075015662318]
  AdapTime is an adaptive temporal reasoning method that dynamically executes reasoning steps based on the input context.<n>It integrates seamlessly with state-of-the-art LLMs and significantly enhances their temporal reasoning capabilities without relying on external support.
  arXiv  Detail & Related papers  (2026-04-27T08:34:40Z)
• METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models [61.33372454250959]
  Contextual causal reasoning is a critical yet challenging capability for Large Language Models.<n>Existing benchmarks fail to ensure context consistency or cover the full causal hierarchy.<n>We pioneer METER to systematically benchmark LLMs across all three levels of the causal ladder.
  arXiv  Detail & Related papers  (2026-04-13T14:07:11Z)
• Saliency-Aware Multi-Route Thinking: Revisiting Vision-Language Reasoning [50.62037276161025]
  Vision-language models (VLMs) aim to reason by jointly leveraging visual and textual modalities.<n>Key obstacle is that visual inputs are typically provided only once at the start of generation.<n>We propose emphSaliency-Aware Principle (SAP) selection.
  arXiv  Detail & Related papers  (2026-02-18T18:49:56Z)
• ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphs [2.9539912037183362]
  Large Language Models (LLMs) demonstrate strong reasoning capabilities but struggle with hallucinations and limited transparency.<n>We propose ProgRAG, a multi-hop knowledge graph question answering (KGQA) framework that decomposes complex questions into sub-questions and extends partial reasoning paths.<n> Experiments on three well-known datasets demonstrate that ProgRAG outperforms existing baselines in multi-hop KGQA.
  arXiv  Detail & Related papers  (2025-11-13T12:14:36Z)
• CLATTER: Comprehensive Entailment Reasoning for Hallucination Detection [60.98964268961243]
  We propose that guiding models to perform a systematic and comprehensive reasoning process allows models to execute much finer-grained and accurate entailment decisions.<n>We define a 3-step reasoning process, consisting of (i) claim decomposition, (ii) sub-claim attribution and entailment classification, and (iii) aggregated classification, showing that such guided reasoning indeed yields improved hallucination detection.
  arXiv  Detail & Related papers  (2025-06-05T17:02:52Z)
• MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM [58.2298313720146]
  Multimodal hallucinations are multi-sourced and arise from diverse causes.<n>Existing benchmarks fail to adequately distinguish between perception-induced hallucinations and reasoning-induced hallucinations.
  arXiv  Detail & Related papers  (2025-05-30T05:54:36Z)
• Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling [1.219841051166348]
  In this paper, we explore the combined potential of in-context search and test-time scaling on super hard reasoning tasks.<n>We find that by employing advanced in-context search prompting to LLMs augmented with internal scaling, one can achieve transformative performance breakthroughs.
  arXiv  Detail & Related papers  (2025-05-28T12:28:18Z)
• Reasoning LLMs are Wandering Solution Explorers [5.3795217858078805]
  This paper formalizes what constitutes systematic problem solving and identifies common failure modes that reveal reasoning LLMs to be wanderers rather than systematic explorers.<n>Our findings suggest that current models' performance can appear to be competent on simple tasks yet degrade sharply as complexity increases.
  arXiv  Detail & Related papers  (2025-05-26T17:59:53Z)
• Failure Modes of LLMs for Causal Reasoning on Narratives [51.19592551510628]
  We investigate the interaction between world knowledge and logical reasoning.<n>We find that state-of-the-art large language models (LLMs) often rely on superficial generalizations.<n>We show that simple reformulations of the task can elicit more robust reasoning behavior.
  arXiv  Detail & Related papers  (2024-10-31T12:48:58Z)
• Concise and Organized Perception Facilitates Reasoning in Large Language Models [31.238220405009617]
  Exploiting large language models (LLMs) to tackle reasoning has garnered growing attention.<n>It still remains highly challenging to achieve satisfactory results in complex logical problems, characterized by plenty of premises within the context and requiring multi-hop reasoning.<n>In this work, we first examine the mechanism from the perspective of information flow and reveal that LLMs confront difficulties akin to human-like cognitive biases when dealing with disordered and irrelevant content in reasoning tasks.
  arXiv  Detail & Related papers  (2023-10-05T04:47:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.