# WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue

arXiv: https://arxiv.org/abs/2511.16544 · HTML: https://mlsanity.com/paper/2511.16544/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 20 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset](https://mlsanity.com/paper/2104.08671/) (2021)
- [Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks](https://mlsanity.com/paper/2410.20266/) (2024)
- [Medical Hallucinations in Foundation Models and Their Impact on Healthcare](https://mlsanity.com/paper/2503.05777/) (2025)
- [Rethinking Evaluation in ASR: Are Our Models Robust Enough?](https://mlsanity.com/paper/2010.11745/) (2020)
- [Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding](https://mlsanity.com/paper/2104.02138/) (2021)
- [PriMock57: A Dataset Of Primary Care Mock Consultations](https://mlsanity.com/paper/2204.00333/) (2022)
- [Semantic-WER: A Unified Metric for the Evaluation of ASR Transcript for End Usability](https://mlsanity.com/paper/2106.02016/) (2021)
- [SeMaScore : a new evaluation metric for automatic speech recognition tasks](https://mlsanity.com/paper/2401.07506/) (2024)
- [H_eval: A new hybrid evaluation metric for automatic speech recognition tasks](https://mlsanity.com/paper/2211.01722/) (2022)
- [Clinical BERTScore: An Improved Measure of Automatic Speech Recognition Performance in Clinical Settings](https://mlsanity.com/paper/2303.05737/) (2023)
- [Aligning ASR Evaluation with Human and LLM Judgments: Intelligibility Metrics Using Phonetic, Semantic, and NLI Approaches](https://mlsanity.com/paper/2506.16528/) (2025)

## Built on by (most cited first, 3 of 3)

- [Development and Feasibility Evaluation of an Edge AI as Medical Device System for Breast Cancer Multidisciplinary Team Meetings](https://mlsanity.com/paper/2608.22108/) (2026)
- [When Patients Cut In: Extending Clinical Conversational AI Safety to Interruptions](https://mlsanity.com/paper/2608.29241/) (2026)
- [Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR](https://mlsanity.com/paper/2610.20461/) (2026)

## Abstract (arXiv)

As Automatic Speech Recognition (ASR) is increasingly deployed in clinical dialogue, standard evaluations still rely heavily on Word Error Rate (WER). This paper challenges that standard, investigating whether WER or other common metrics correlate with the clinical impact of transcription errors. We establish a gold-standard benchmark by having expert clinicians compare ground-truth utterances to their ASR-generated counterparts, labeling the clinical impact of any discrepancies found in two distinct doctor-patient dialogue datasets. Our analysis reveals that WER and a comprehensive suite of existing metrics correlate poorly with the clinician-assigned risk labels (No, Minimal, or Significant Impact). To bridge this evaluation gap, we introduce an LLM-as-a-Judge, programmatically optimized using GEPA through DSPy to replicate expert clinical assessment. The optimized judge (Gemini-2.5-Pro) achieves human-comparable performance, obtaining 90% accuracy and a strong Cohen's kappa of 0.816. This work provides a validated, automated framework for moving ASR evaluation beyond simple textual fidelity to a necessary, scalable assessment of safety in clinical dialogue.