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

arXiv: https://arxiv.org/abs/2607.28421 · HTML: https://mlsanity.com/paper/2607.28421/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 57 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 30 of 32)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [Unifying distillation and privileged information](https://mlsanity.com/paper/1511.03643/) (2015)
- [Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer](https://mlsanity.com/paper/1711.06664/) (2017)
- [Cross Modal Distillation for Supervision Transfer](https://mlsanity.com/paper/1507.00448/) (2015)
- [Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence](https://mlsanity.com/paper/2210.13701/) (2022)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [PaPaGei: Open Foundation Models for Optical Physiological Signals](https://mlsanity.com/paper/2410.20542/) (2024)
- [OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data](https://mlsanity.com/paper/2510.02410/) (2025)
- [Toward Understanding Privileged Features Distillation in Learning-to-Rank](https://mlsanity.com/paper/2209.08754/) (2022)
- [PhysioLLM: Supporting Personalized Health Insights with Wearables and Large Language Models](https://mlsanity.com/paper/2406.19283/) (2024)
- [Learning Game-Playing Agents with Generative Code Optimization](https://mlsanity.com/paper/2508.19506/) (2025)
- [SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model](https://mlsanity.com/paper/2601.21031/) (2026)
- [Understanding the Challenges in Iterative Generative Optimization with LLMs](https://mlsanity.com/paper/2603.23994/) (2026)
- [PPG-Distill: Efficient Photoplethysmography Signals Analysis via Foundation Model Distillation](https://mlsanity.com/paper/2509.19215/) (2025)
- [SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis](https://mlsanity.com/paper/2606.24235/) (2026)
- [A robust PPG foundation model using multimodal physiological supervision](https://mlsanity.com/paper/2606.07365/) (2026)

## Abstract (arXiv)

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.