REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment

• URL: http://arxiv.org/abs/2608.07931v1
• Date: Sat, 08 Aug 2026 05:37:13 GMT
• Title: REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment
• Abstract summary: Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment.<n>We propose REIN, an alignment framework that trains LRMs to produce a structured reasoning sequence.<n>REIN introduces a reward mechanism that encourages explicit abstention when none of the sampled reasoning chains yields a correct answer.
• Score: 35.47736821237044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment. Hallucinations in LRMs arise from two distinct failure sources: reasoning hallucination, where flawed inference steps propagate to an incorrect conclusion, and knowledge hallucination, where the model lacks the requisite factual knowledge to answer the query. To address reasoning hallucination, we propose REIN, an alignment framework that trains LRMs to produce a structured reasoning sequence, $\texttt{<think>} $$\rightarrow$ $\texttt{<reflection>} $$\rightarrow$ $\texttt{<answer>}$, enabling explicit self-reflection before committing to a final answer. To address knowledge hallucination, REIN introduces a reward mechanism that encourages explicit abstention (e.g., "I don't know") when none of the sampled reasoning chains yields a correct answer, allowing the model to refrain from unsupported predictions. Extensive evaluations on mathematical and commonsense reasoning benchmarks show that REIN consistently improves selective accuracy, reduces incorrect-but-self-endorsed responses, and maintains high coverage compared with competitive baselines. Notably, REIN achieves these gains within a single forward pass, without requiring process supervision, inference-time controllers, external search, or multi-round critiques. Experiments on multiple backbones show that REIN reduces the hallucination proxy by $58\sim72\%$ relative to the base models while maintaining $86\sim91\%$ average coverage, and improves selective accuracy on attempted questions by $6.6\sim14.2\%$.

Related papers

• BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation [51.22170603236523]
  We propose a Balanced Token-level Policy Optimization framework for hallucination mitigation.<n>BalTO extracts checkable factual claims, verifies them against the reference context, and projects claim-level judgments to token-level labels.<n>Experiments on ConFiQA, RAGTruth, and FinLLM-Eval show that BALTO achieves the highest faithfulness across all six model--benchmark settings.
  arXiv  Detail & Related papers  (2026-06-14T16:25:59Z)
• Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty [33.04999074297977]
  E-GRM is an efficient generative reward modeling framework grounded in model-internal uncertainty.<n>We show that E-GRM substantially reduces inference cost while consistently improving answer accuracy.
  arXiv  Detail & Related papers  (2026-04-11T07:35:08Z)
• From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG [65.0203623486525]
  Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering.<n>Their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields.<n>Existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning.
  arXiv  Detail & Related papers  (2026-02-06T08:25:30Z)
• CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models [29.703793991791674]
  Existing RAG-oriented reinforcement learning methods rely on external rewards that often fail to evaluate document faithfulness.<n>We propose a novel "internal-external" hybrid reward framework centered on a Contrastive Likelihood Reward (CLR)<n>CLR directly optimize the log-likelihood gap between responses conditioned on prompts with and without supporting evidence.
  arXiv  Detail & Related papers  (2026-02-02T12:21:59Z)
• Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models [72.4149653187766]
  We propose a Reasoner-Verifier framework named Adrialversa Reasoning RAG (ARR)<n>The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage.<n> Experiments on multiple benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2026-01-08T06:57:03Z)
• Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning [46.106795445750855]
  REFRAIN is a training-free framework that determines when to stop reasoning to mitigate overthinking.<n> REFRAIN reduces token usage by 20-55% while maintaining or improving accuracy compared to standard CoT prompting.
  arXiv  Detail & Related papers  (2025-10-11T08:30:00Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs [35.27561531876348]
  This paper systematically investigates the impact of Reinforcement Learning with Verifiable Rewards (RLVR) on Large Language Models (LLMs)<n>We show that RLVR can extend the reasoning boundary for both mathematical and coding tasks.<n>We present a theoretical framework explaining RLVR's incentive mechanism, demonstrating how it can encourage correct reasoning even when rewards are based solely on answer correctness.
  arXiv  Detail & Related papers  (2025-06-17T07:06:56Z)
• Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models [12.270274049887298]
  Reasoning traces can be redundant or logically inconsistent, making them a new source of hallucination.<n>Existing hallucination detection methods focus primarily on answer-level uncertainty.<n>We propose RACE, a novel framework specifically tailored for hallucination detection in LRMs.
  arXiv  Detail & Related papers  (2025-06-05T09:54:04Z)
• Are Reasoning Models More Prone to Hallucination? [70.04436965009072]
  Recently evolved large reasoning models (LRMs) show powerful performance in solving complex tasks with long chain-of-thought (CoT) reasoning capability.<n>Are reasoning models more prone to hallucination?<n>This paper addresses the question from three perspectives.
  arXiv  Detail & Related papers  (2025-05-29T16:53:41Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)

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.