When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence

• URL: http://arxiv.org/abs/2607.28421v1
• Date: Thu, 30 Jul 2026 16:01:17 GMT
• Title: When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence
• Abstract summary: Derived measurements increasingly enter large language model (LLM) pipelines as direct facts despite their instance-dependent validity.<n>We define derived-feature over-trust (DFOT) as the failure in which a downstream LLM assigns such a measurement status of a direct fact.<n>Five estimands quantify this chain: conflict over-trust rate (COTR), context-induced error rate (CIR), correct repair rate (CRR), evidence-specific repair margin (ESRM) and utility harm rate (UHR)
• Score: 23.663230810212042
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Derived measurements increasingly enter large language model (LLM) pipelines as direct facts despite their instance-dependent validity. We define derived-feature over-trust (DFOT) as the failure in which a downstream LLM assigns such a measurement the epistemic status of a direct fact or uses it outside its valid scope. Using physiological sensing as a case study, D1 tests acceptance of a PPG-derived rhythm contradicted by offline ECG, whereas D2 tests rejection of an offline-confirmed reliable PPG rhythm under misleading severe history. ECG supplies training supervision and offline reference construction but is never shown to the LLM. Five estimands quantify this chain: conflict over-trust rate (COTR) and context-induced error rate (CIR) characterize D1/D2; correct repair rate (CRR) measures frozen-error repair; evidence-specific repair margin (ESRM) contrasts matched and patient-disjoint shuffled evidence; and utility harm rate (UHR) measures unnecessary verification among HIGH-reliability cases used without verification at baseline. The framework does not depend on a particular reliability generator. We demonstrate it on 50,000 paired PPG-ECG records using ECG-to-PPG privileged distillation as an illustrative baseline and PPG-only inference. On a protocol-locked 187-patient test, the baseline improves four repair and specificity endpoints by 1.82-6.69 percentage points, with all paired confidence intervals excluding zero; UHR increases by 0.67 percentage points (95% CI: -0.4 to +1.7). DFOT provides a common evaluation target for stronger mitigation methods. The code is available at https://github.com/Zongheng-Guo/When-Derived-Measurements-Mislead.

Related papers

• Reversibility-Verified De-identification for Cloud-Local LLM Inference: A Locally Certified Dehydrate-Rehydrate Loop with Layered Assurance (DR-SL) [1.802678437602184]
  DR-SL (Dehydrate-Rehydrate with Self-Learning loop) formalizes de-identification completeness as two measurable conditions.<n>A fully local two-branch verifier iterates dehydration under a lexicographic gate with guaranteed termination.<n>We prove Fano-type lower bounds, a Pufferfish witness, and a rate-privacy feasibility criterion, and state their scope plainly.
  arXiv  Detail & Related papers  (2026-09-14T01:04:58Z)
• CARD: Calibration via Agreement in Reverse Diffusion for Out-of-Domain MRI Segmentation [14.844162865265673]
  We propose CARD, which maps the temporal aggregate of disagreement to a temperature field applied per pixel across all classes, so that confidence changes while the segmentation does not.<n>Across cardiac, prostate and brain MRI shifts, CARD lowers calibration error in 45 of 49 comparisons against the strongest baseline in each setting.
  arXiv  Detail & Related papers  (2026-08-26T07:23:08Z)
• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
  This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
  arXiv  Detail & Related papers  (2026-07-29T05:16:59Z)
• Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs [4.721990925113432]
  Aligned language models routinely misreport under non-evidential pressure.<n>We study the two demands, resist (ignore forbidden pressure) and update (follow licensed evidence)<n>We causally localize low-rank report coordinates for answer, confidence, and caveat.
  arXiv  Detail & Related papers  (2026-07-14T17:28:25Z)
• SafeImpute: Reliable Clinical Data Imputation via Conformal Selection [35.40404498771435]
  Clinical care often relies on key laboratory indicators, yet real-world patient visits are sparse and tests are ordered irregularly.<n>We study reliable clinical imputation, aiming to produce accurate imputations while selectively releasing the reliable results.<n>We propose SafeImpute, a reliable imputation framework for irregular and sparse clinical longitudinal records.
  arXiv  Detail & Related papers  (2026-07-06T20:16:21Z)
• What Accuracy and Gradient Cosine Miss: Evaluating Feedback Alignment via Scale Stability, Reference Validity, and Depth Utility [48.10132234701036]
  We propose a diagnostic evaluation protocol based on three checks -- scale stability, reference validity, and depth utility -- together with per-layer rather than aggregate cosine reporting.<n>Across multiple architectures and methods, our protocol identifies all failures with wide calibration margins.
  arXiv  Detail & Related papers  (2026-06-19T06:04:17Z)
• Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports [49.5225801722164]
  Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar.<n>We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance.
  arXiv  Detail & Related papers  (2026-06-17T08:10:30Z)
• Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation [0.0]
  We propose a two-stage pipeline for treatment effect estimation from incomplete longitudinal EHRs.<n>CaulFlow-T, a directed acyclic graph (DAG)-constrained normalizing flow with long short-term memory (LSTM)-encoded patient history.<n>CaulFlow-T performs exact invertible counterfactual inference, avoiding approximation errors from variational inference and separating confounding through explicit causal structure.
  arXiv  Detail & Related papers  (2026-05-06T16:53:08Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• Counterfactual Peptide Editing for Causal TCR--pMHC Binding Inference [0.0]
  Neural models for TCR-pMHC binding prediction are susceptible to shortcut learning.<n>We introduce emphCounterfactual Invariant Prediction (CIP), a training framework that generates biologically constrained counterfactual peptide edits.
  arXiv  Detail & Related papers  (2026-04-14T19:40:46Z)
• FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning [49.65751420291115]
  Chain-of-Thought (CoT) prompting has improved LLM reasoning, but models often generate explanations that appear coherent while containing unfaithful intermediate steps.<n>We propose FACT-E, a causality-inspired framework for evaluating CoT quality.<n>We show that FACT-E improves reasoning-trajectory selection and yields stronger in-context learnings.
  arXiv  Detail & Related papers  (2026-04-12T15:35:08Z)
• PUNCH: Physics-informed Uncertainty-aware Network for Coronary Hemodynamics [8.812266680285369]
  We introduce a non-diagnosed, uncertainty-aware framework for estimating coronary flow reserve directly from standard angiography.<n>The system integrates physics-informed neural networks with variational inference to infer coronary blood flow from first-principles models of contrast transport.<n>The pipeline runs in approximately three minutes per patient on a single GPU, with no population-level training.
  arXiv  Detail & Related papers  (2026-01-23T21:47:23Z)
• Conditional Coverage Diagnostics for Conformal Prediction [47.93989136542648]
  We show that conditional coverage estimation can be a classification problem.<n>We call the resulting family of metrics excess risk of the target coverage (ERT)<n>We release an open-source package for ERT as well as previous conditional coverage metrics.
  arXiv  Detail & Related papers  (2025-12-12T18:47:39Z)
• 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)

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.