Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.16544 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914262486614016 |
|---|---|
| author | Ellis, Zachary Joselowitz, Jared Deo, Yash He, Yajie Kalygina, Anna Higham, Aisling Rahimzadeh, Mana Jia, Yan Habli, Ibrahim Lim, Ernest |
| author_facet | Ellis, Zachary Joselowitz, Jared Deo, Yash He, Yajie Kalygina, Anna Higham, Aisling Rahimzadeh, Mana Jia, Yan Habli, Ibrahim Lim, Ernest |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_16544 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue Ellis, Zachary Joselowitz, Jared Deo, Yash He, Yajie Kalygina, Anna Higham, Aisling Rahimzadeh, Mana Jia, Yan Habli, Ibrahim Lim, Ernest Computation and Language Artificial Intelligence 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. |
| title | WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2511.16544 |