SAR-LM: Symbolic Audio Reasoning with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911256275845120 |
|---|---|
| author | Taheri, Termeh Ma, Yinghao Benetos, Emmanouil |
| author_facet | Taheri, Termeh Ma, Yinghao Benetos, Emmanouil |
| contents | Large language models (LLMs) have advanced in text and vision, but their reasoning on audio remains limited. Most existing methods rely on dense audio embeddings, which are difficult to interpret and often fail on structured reasoning tasks. Caption-based approaches, introduced in recent benchmarks such as MMAU, improve performance by translating audio into text, yet still depend on dense embeddings as input, offering little insight when models fail.
We present SAR-LM, a symbolic audio reasoning pipeline that builds on this caption-based paradigm by converting audio into structured, human-readable features across speech, sound events, and music. These symbolic inputs support both reasoning and transparent error analysis, enabling us to trace failures to specific features. Across three benchmarks, MMAU, MMAR, and OmniBench, SAR-LM achieves competitive results, while prioritizing interpretability as its primary contribution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06483 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAR-LM: Symbolic Audio Reasoning with Large Language Models Taheri, Termeh Ma, Yinghao Benetos, Emmanouil Sound Large language models (LLMs) have advanced in text and vision, but their reasoning on audio remains limited. Most existing methods rely on dense audio embeddings, which are difficult to interpret and often fail on structured reasoning tasks. Caption-based approaches, introduced in recent benchmarks such as MMAU, improve performance by translating audio into text, yet still depend on dense embeddings as input, offering little insight when models fail. We present SAR-LM, a symbolic audio reasoning pipeline that builds on this caption-based paradigm by converting audio into structured, human-readable features across speech, sound events, and music. These symbolic inputs support both reasoning and transparent error analysis, enabling us to trace failures to specific features. Across three benchmarks, MMAU, MMAR, and OmniBench, SAR-LM achieves competitive results, while prioritizing interpretability as its primary contribution. |
| title | SAR-LM: Symbolic Audio Reasoning with Large Language Models |
| topic | Sound |
| url | https://arxiv.org/abs/2511.06483 |