MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914613948317696 |
|---|---|
| author | Rajgarhia, Harshit Ojha, Shuubham Shaik, Asif Pothanapalli, Akhil Lokesh, Rachuri Mukherji, Abhishek Desikan, Prasanna |
| author_facet | Rajgarhia, Harshit Ojha, Shuubham Shaik, Asif Pothanapalli, Akhil Lokesh, Rachuri Mukherji, Abhishek Desikan, Prasanna |
| contents | Medical audio data is difficult to collect due to privacy regulations and high annotation costs arising from domain expertise. Thus, existing benchmarks tend to underrepresent complex medical audio scenarios. To address this challenge, we present MedMosaic, a medical audio question-answering dataset designed to benchmark language and audio reasoning models under realistic clinical constraints. MedMosaic features a diverse range of medical audio types, including condition-related physiological sounds, carefully constructed synthetic voices to mimic speech with artifacts as well as real short and long length clinical conversations to model varying context lengths. The dataset also features a total of 46,701 question-answer pairs, spanning categories such as multiple-choice, sequential multi-turn, and open-ended question-answers, enabling systematic evaluation of multi-hop reasoning and answer generation capabilities. Benchmarking 13 audio and multimodal reasoning models reveals that reasoning remains challenging for all evaluated systems, with substantial performance variation across question types. In particular, even state-of-the-art model like Gemini-2.5-pro can only achieve 68.1% accuracy approximately. These findings underscore persistent limitations in medical reasoning and highlight the need for more robust, domain-specific multimodal reasoning models. A sample of benchmark data is available here: https://shorturl.at/Lyp33 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00969 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio Rajgarhia, Harshit Ojha, Shuubham Shaik, Asif Pothanapalli, Akhil Lokesh, Rachuri Mukherji, Abhishek Desikan, Prasanna Sound Artificial Intelligence Computation and Language Medical audio data is difficult to collect due to privacy regulations and high annotation costs arising from domain expertise. Thus, existing benchmarks tend to underrepresent complex medical audio scenarios. To address this challenge, we present MedMosaic, a medical audio question-answering dataset designed to benchmark language and audio reasoning models under realistic clinical constraints. MedMosaic features a diverse range of medical audio types, including condition-related physiological sounds, carefully constructed synthetic voices to mimic speech with artifacts as well as real short and long length clinical conversations to model varying context lengths. The dataset also features a total of 46,701 question-answer pairs, spanning categories such as multiple-choice, sequential multi-turn, and open-ended question-answers, enabling systematic evaluation of multi-hop reasoning and answer generation capabilities. Benchmarking 13 audio and multimodal reasoning models reveals that reasoning remains challenging for all evaluated systems, with substantial performance variation across question types. In particular, even state-of-the-art model like Gemini-2.5-pro can only achieve 68.1% accuracy approximately. These findings underscore persistent limitations in medical reasoning and highlight the need for more robust, domain-specific multimodal reasoning models. A sample of benchmark data is available here: https://shorturl.at/Lyp33 |
| title | MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio |
| topic | Sound Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.00969 |