Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement

• URL: http://arxiv.org/abs/2608.10725v1
• Date: Tue, 11 Aug 2026 09:43:14 GMT
• Title: Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement
• Abstract summary: We propose a two-stage framework for medical hypothesis verification in multiple-choice settings.<n>We show that abstention is not random but reflects genuine uncertainty, with abstained predictions associated with lower confidence.<n>Our experiments conducted on MedReason and MedQA show that abstention can be repurposed as a control signal for selective reasoning refinement.
• Score: 8.78288626457356
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models to abstain when uncertain improves reliability but introduces a coverage accuracy tradeoff. We propose a two-stage framework for medical hypothesis verification in multiple-choice settings that manages this tradeoff through targeted ontology grounding, applied only when the model abstains. We show that abstention is not random but reflects genuine uncertainty, with abstained predictions associated with lower confidence. Across two frontier models (GPT-5.5, accessed via the Azure OpenAI API, and DeepSeek-R1), the proposed framework improves question-level accuracy by 9.6 percentage points (82.9% to 92.5%) and hypothesis-level accuracy by 4.2 percentage points (92.0% to 96.2%). Our experiments conducted on MedReason and MedQA show that abstention can be repurposed as a control signal for selective reasoning refinement, achieving knowledge-graph-level performance without explicit knowledge graph construction.

Related papers

• Bayesian uncertainty estimation improves clinical decision making in medical AI agents [3.251669068529209]
  We show that Monte Carlo dropout provides an uncertainty signal that tracks generalisation across training-set scales and flags confident yet error-prone predictions.<n>In a controlled 2x2 factorial experiment, a clinical-decision-support agent exploited this uncertainty only when it was delivered as a binary error-risk flag rather than as raw scores.
  arXiv  Detail & Related papers  (2026-07-22T11:54:23Z)
• LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data [2.1443570696048906]
  Large language models (LLMs) are increasingly applied to structured clinical data.<n>We compare Qwen 2.5 7B and XGBoost on a prediction task via attribution divergence analysis.
  arXiv  Detail & Related papers  (2026-06-17T18:49:44Z)
• Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know" [47.930782177987446]
  Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations.<n>We evaluate three task-equivalent prompting regimes: Direct, Assistive, and Incremental, across different model scales and multi-hop QA benchmarks.<n>Because factual knowledge is stable while hallucinations are agreement, cross-regime provides a precise signal of internal uncertainty.
  arXiv  Detail & Related papers  (2026-02-04T18:39:58Z)
• Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty [7.985656420275706]
  We introduce MedAbstain, a unified benchmark and evaluation protocol for abstention in medical multiple-choice question answering.<n>We show that even state-of-the-art, high-accuracy models often fail to abstain with uncertain.
  arXiv  Detail & Related papers  (2026-01-18T16:19:29Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Uncertainty-Driven Reliability: Selective Prediction and Trustworthy Deployment in Modern Machine Learning [1.2183405753834562]
  This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of machine learning (ML) systems.<n>We first show that a model's training trajectory contains rich uncertainty signals that can be exploited without altering its architecture or loss.<n>We propose a lightweight, post-hoc abstention method that works across tasks, avoids the cost of deep ensembles, and achieves state-of-the-art selective prediction performance.
  arXiv  Detail & Related papers  (2025-08-11T02:33:53Z)
• Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization [0.06554326244334867]
  This paper introduces Preferred-MedLLM-Qwen-72B, a 72B- parameter model optimized for the Japanese medical domain.<n>We employ a two-stage fine-tuning process on the Qwen2.5-72B base model to achieve both high accuracy and stable reasoning.
  arXiv  Detail & Related papers  (2025-04-25T05:15:31Z)
• Benchmarking Reasoning Robustness in Large Language Models [76.79744000300363]
  We find significant performance degradation on novel or incomplete data.<n>These findings highlight the reliance on recall over rigorous logical inference.<n>This paper introduces a novel benchmark, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps.
  arXiv  Detail & Related papers  (2025-03-06T15:36:06Z)
• Improving Selective Visual Question Answering by Learning from Your Peers [74.20167944693424]
  Visual Question Answering (VQA) models can have difficulties abstaining from answering when they are wrong. We propose Learning from Your Peers (LYP) approach for training multimodal selection functions for making abstention decisions. Our approach uses predictions from models trained on distinct subsets of the training data as targets for optimizing a Selective VQA model.
  arXiv  Detail & Related papers  (2023-06-14T21:22:01Z)
• Conservative Prediction via Data-Driven Confidence Minimization [70.93946578046003]
  In safety-critical applications of machine learning, it is often desirable for a model to be conservative. We propose the Data-Driven Confidence Minimization framework, which minimizes confidence on an uncertainty dataset.
  arXiv  Detail & Related papers  (2023-06-08T07:05:36Z)
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty [57.023423137202485]
  Concerns regarding the reliability of medical image segmentation persist among clinicians.<n>We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.<n>By leveraging subjective logic theory, we explicitly model probability and uncertainty for medical image segmentation.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)
• Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions [121.10450359856242]
  We develop a frequentist procedure that utilizes influence functions of a model's loss functional to construct a jackknife (or leave-one-out) estimator of predictive confidence intervals. The DJ satisfies (1) and (2), is applicable to a wide range of deep learning models, is easy to implement, and can be applied in a post-hoc fashion without interfering with model training or compromising its accuracy.
  arXiv  Detail & Related papers  (2020-06-29T13:36:52Z)

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.