# AC/DC: LLM-based Audio Comprehension via Dialogue Continuation

Source: [AC/DC: LLM-based Audio Comprehension via Dialogue Continuation](<https://www.sota2.com/research/paper/68fa79541e209131cea7d1ac>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:56:50.224Z

Authors: Yusuke Fujita, Tomoya Mizumoto, Atsushi Kojima, Lianbo Liu, Yui Sudo

Published: 2025-06-12T02:48:47.000Z

## Abstract

We propose an instruction-following audio comprehension model that leverages the dialogue continuation ability of large language models (LLMs). Instead of directly generating target captions in training data, the proposed method trains a model to produce responses as if the input caption triggered a dialogue. This dialogue continuation training mitigates the caption variation problem. Learning to continue a dialogue effectively captures the caption's meaning beyond its surface-level words. As a result, our model enables zero-shot instruction-following capability without multitask instruction tuning, even trained solely on audio captioning datasets. Experiments on AudioCaps, WavCaps, and Clotho datasets with AudioBench audio-scene question-answering tests demonstrate our model's ability to follow various unseen instructions.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.10312>)

[PDF](<https://arxiv.org/pdf/2506.10312.pdf>)
