# AR&D: A Framework for Retrieving and Describing Concepts for Interpreting AudioLLMs

arXiv: https://arxiv.org/abs/2602.22253 · HTML: https://mlsanity.com/paper/2602.22253/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2026.

## Built on by (most cited first, 1 of 1)

- [Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models](https://mlsanity.com/paper/2608.06409/) (2026)

## Abstract (arXiv)

Despite strong performance in audio perception tasks, large audio-language models (AudioLLMs) remain opaque to interpretation. A major factor behind this lack of interpretability is that individual neurons in these models frequently activate in response to several unrelated concepts. We introduce the first mechanistic interpretability framework for AudioLLMs, leveraging sparse autoencoders (SAEs) to disentangle polysemantic activations into monosemantic features. Our pipeline identifies representative audio clips, assigns meaningful names via automated captioning, and validates concepts through human evaluation and steering. Experiments show that AudioLLMs encode structured and interpretable features, enhancing transparency and control. This work provides a foundation for trustworthy deployment in high-stakes domains and enables future extensions to larger models, multilingual audio, and more fine-grained paralinguistic features. Project URL: https://townim-faisal.github.io/AutoInterpret-AudioLLM/