mlsanityData to 14 Oct 2026

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs

arXiv 2505.13529 ↗First posted 18 May 2025cs.AI cs.CL cs.LGcited by 8

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Recent advances in Large Reasoning Models (LRMs) have shown impressive capabilities in mathematical and logical reasoning. However, current LRMs rarely admit ignorance or respond with "I don't know". Instead, they often produce incorrect answers while showing undue confidence, raising concerns about their factual reliability. In this work, we identify two pathological reasoning patterns characterized by overthinking that contribute to the overconfident and incorrect answers: last-minute guessing and second-thought spiraling. To address these issues, we propose BARREL-a novel framework that promotes concise and boundary-aware factual reasoning. Our experiments show that BARREL-training increases the reliability of DeepSeek-R1-Distill-Llama-8B from 39.33% to 61.48%, while still achieving accuracy comparable to models finetuned on reasoning data generated by R1. These results demonstrate that our pilot study is inspiring to build more reliable and factual System 2 LRMs.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 27 of its 41 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

27 of 41 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities23 Mar
  2. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs30 Dec

Other references · 25

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  6. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  7. 2024OpenAI o1 System Cardcited by 1,244
  8. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  9. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 982
  10. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  11. 2022Self-critiquing models for assisting human evaluatorscited by 380
  12. 2024Measuring short-form factuality in large language modelscited by 373
13 more
  1. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 244
  2. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
  3. 2024SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationalescited by 105
  4. 2024Large Language Models Must Be Taught to Know What They Don't Knowcited by 100
  5. 2024LLM Internal States Reveal Hallucination Risk Faced With a Querycited by 82
  6. 2024Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedbackcited by 66
  7. 2025Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Modelscited by 52
  8. 2024Can AI Assistants Know What They Don't Know?cited by 50
  9. 2024FLAME: Factuality-Aware Alignment for Large Language Modelscited by 47
  10. 2024Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigationcited by 44
  11. 2024Knowledge Boundary of Large Language Models: A Surveycited by 40
  12. 2024Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanationscited by 30
  13. 2024UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Modelscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2025Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoningcited by 106
  2. 2026BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Searchcited by 3
  3. 2026Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Modelscited by 3
  4. 2026Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learningcited by 3
  5. 2026REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignmentcited by 1
  6. 2026From Refuse to Richness: Rubric Rewards for Long-Form Hallucination Reinforcement Learningcited by 1
  7. 2025Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundarycited by 0
  8. 2025Enhancing Reliability across Short and Long-Form QA via Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs
  2. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models
  3. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
  4. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
  5. 2025THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models
  6. 2025Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
  7. 2026RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models
  8. 2025Efficient Inference for Large Reasoning Models: A Survey