Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA

• URL: http://arxiv.org/abs/2609.09684v1
• Date: Wed, 09 Sep 2026 03:58:59 GMT
• Title: Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA
• Abstract summary: We propose root-mean-square Robustness-based Sample Prioritization (RMS-RSP) to perturb hidden states at rationale tokens.<n> RMS-RSP improves robust accuracy and semantic consistency by 1.91 and 2.85 points on average, with the same direction on all five datasets.
• Score: 12.797519888387628
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Medical question-answering datasets often contain answer labels, whereas high-quality rationales remain scarce, noisy, or costly to validate. This changes the acquisition question: rather than asking which questions should be labeled, we ask which already-labeled questions should receive rationale supervision under a fixed token budget. We study an offline version of this problem in which candidate rationales are visible to the selector but withheld from downstream training unless selected. We propose root-mean-square Robustness-based Sample Prioritization (RMS-RSP), which perturbs hidden states only at rationale tokens and measures the resulting shift in the gold-versus-best-distractor margin. Across five medical QA datasets, MedGemma-4B-IT, three training seeds, ten budgeted non-RSP selectors, and an unbudgeted full-supervision reference, RMS-RSP provides a deliberately qualified result. Its locked-budget accuracy is 60.61% on average versus 60.08% for Random, with a statistically resolved gain only on AfriMed-QA (+1.44 points). Its full-budget accuracy area is not better than Random. However, after three answer-option reorderings, RMS-RSP improves robust accuracy and semantic consistency by 1.91 and 2.85 points on average, respectively, with the same direction on all five datasets. Training on every pool rationale raises macro accuracy to 63.74%, but consumes 29--254 times more rationale tokens and does not uniformly improve robustness. These findings do not establish universal accuracy gains; they instead suggest that rationale-local boundary sensitivity can identify supervision that improves invariance to semantically equivalent formatting changes.

Related papers

• Adaptive Conformal Redistribution for Inter-class Transitional Uncertainty in Medical Image Classification [9.578682349231789]
  adaptive conformal redistribution (AdaConRed) is a label-free post-conformal decision rule that converts ambiguous prediction sets into refined class assignments.<n>AdaConRed outperforms LAC, APS and RAPS under an identical backbone and redistribution rule.<n>Conformal prediction can be extended beyond uncertainty toward actionable decision support where transitional disease categories are present.
  arXiv  Detail & Related papers  (2026-09-10T06:21:30Z)
• PruneShift: A Framework for Evaluating Decision Reliability in Structured Pruning [1.8023933646971537]
  Structured pruning uses surrogate objectives because direct task evaluation over every feasible mask is too expensive.<n>We introduce PruneShift, an evaluation framework that separates broad predictive fidelity, fidelity near selector outputs, and the quality of the selected pruning decision.
  arXiv  Detail & Related papers  (2026-08-30T12:52:16Z)
• Know Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented Generation [10.60293484295824]
  We formulate adaptive RAG as calibrated retrieval-budget allocation.<n>We calibrate sequence log-probability and prefix-logit uncertainty signals into probabilities of correctness.<n>For sequence log-probability, ECE drops from 0.275 to 0.062 on TriviaQA, 0.643 to 0.009 on NQ, and 0.711 to 0.031 on MS MARCO.
  arXiv  Detail & Related papers  (2026-06-29T08:36:33Z)
• TriageRA-CCF: Source-Side Clinical Confidence and Coverage Signals for Adaptive Rank Budgeting in Medical LLMs [8.601855281320903]
  TriageRA-CCF is a source-side teacher for adaptive rank-budgeted medical large language models.<n>It combines three signals computed only from source training data: base-model answer confidence, metadata-cell clinical coverage, and a counterfactual close-miss proxy.<n>Under a matched CMB-source training protocol, TriageRA-CCF achieves the best average accuracy among LoRA, DoRA, and MoELoRA baselines.
  arXiv  Detail & Related papers  (2026-06-28T12:52:07Z)
• The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning [54.0056619145783]
  Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback.<n>We identify a hidden bias in PRMs caused by severe imbalance in step-level training data.<n>We propose PRISM, a policy-aware PRM training framework that learns from contrastive step-level comparisons.
  arXiv  Detail & Related papers  (2026-06-08T06:22:33Z)
• Instance-Optimal Estimation with Multiple LLM Judges on a Budget [84.31744861038106]
  We formalize this question as *budgeted heteroskedastic multi-judge estimation*.<n>Given $K$ prompt-response pairs, $J$ judges with known costs, and unknown query-judge variances, the goal is to estimate a bounded score vector while minimizing an $ell_p$-error.<n>We prove that EST-IVWE matches the oracle IVWE rate up to lower-order terms in the budget.
  arXiv  Detail & Related papers  (2026-05-22T08:26:08Z)
• Step-wise Rubric Rewards for LLM Reasoning [72.17879367869503]
  Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models.<n>We find 18.2% of steps in correct responses are wrong yet positively rewarded.<n>Across six mathematical reasoning benchmarks, SRaR improves average accuracy over RaR by 3.57 points.
  arXiv  Detail & Related papers  (2026-05-17T07:08:14Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning [8.024041325202612]
  Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths.<n>We introduce a conformal procedure for CoT reasoning that directly addresses aggregation uncertainty.<n>Our approach replaces majority voting with weighted score aggregation over reasoning paths and calibrates an abstention rule using conformal risk control.
  arXiv  Detail & Related papers  (2026-05-13T20:33:59Z)
• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering [15.39457034915546]
  We present a formal problem formulation for textitReliable Audio-Visual Question Answering ($mathcalR$-AVQA), where we prefer abstention over answering incorrectly.<n>We propose Adaptive Confidence Refinement (ACR), a lightweight method to further enhance the performance of $mathcalR$-AVQA.
  arXiv  Detail & Related papers  (2026-02-04T08:35:33Z)
• Self-Evaluation Guided Beam Search for Reasoning [61.523627290397556]
  We introduce a stepwise self-evaluation mechanism to guide and calibrate the reasoning process of Large Language Model (LLM) We propose a decoding algorithm integrating the self-evaluation guidance via beam search. Our approach surpasses the corresponding Codex-backboned baselines in few-shot accuracy by $6.34%$, $9.56%$, and $5.46%$ on the GSM8K, AQuA, and StrategyQA.
  arXiv  Detail & Related papers  (2023-05-01T02:37:59Z)
• Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification [54.174146346387204]
  We propose an approach named probabilistic uncertainty guided progressive label refinery (P$2$LR) for domain adaptive person re-identification. A quantitative criterion is established to measure the uncertainty of pseudo labels and facilitate the network training. Our method outperforms the baseline by 6.5% mAP on the Duke2Market task, while surpassing the state-of-the-art method by 2.5% mAP on the Market2MSMT task.
  arXiv  Detail & Related papers  (2021-12-28T07:40:12Z)

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.