# Audio Question Answering with GRPO-Based Fine-Tuning and Calibrated Segment-Level Predictions

Source: [Audio Question Answering with GRPO-Based Fine-Tuning and Calibrated Segment-Level Predictions](<https://www.sota2.com/research/paper/691d4f18d6b0dd334292d7b9>)

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

Data updated: 2025-11-20T05:03:41.519Z

Authors: Marcel Gibier, Nolwenn Celton, Rapha\\"el Duroselle, Pierre Serrano, Olivier Boeffard, Jean-Fran\\c{c}ois Bonastre

Published: 2025-11-18T10:05:36.000Z

## Abstract

In this report, we describe our submission to Track 5 of the DCASE 2025 Challenge for the task of Audio Question Answering(AQA). Our system leverages the SSL backbone BEATs to extract frame-level audio features, which are then processed by a classification head to generate segment-level predictions of acoustic events, following the Audioset ontology. These segment-level predictions are subsequently calibrated before producing event-level predictions. Finally, these predictions are incorporated into a structured prompt, along with the question and candidate answers. This prompt is then fed to a fine-tuned version of Qwen2.5-7B-Instruct, trained using the GRPO algorithm with a simple reward function. Our method achieves an accuracy of 62.6 % on the development set, demonstrating the effectiveness of combining acoustic event reasoning with instruction-tuned large language models for AQA.

## 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/2511.14307>)

[PDF](<https://arxiv.org/pdf/2511.14307.pdf>)