# EvA: An Evidence-First Audio Understanding Paradigm for LALMs

arXiv: https://arxiv.org/abs/2603.27667 · HTML: https://mlsanity.com/paper/2603.27667/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://mlsanity.com/paper/2303.17395/) (2023)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities](https://mlsanity.com/paper/2406.11768/) (2024)
- [MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2506.04779/) (2025)
- [Mustango: Toward Controllable Text-to-Music Generation](https://mlsanity.com/paper/2311.08355/) (2023)
- [Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models](https://mlsanity.com/paper/2503.02318/) (2025)
- [The Benefit Of Temporally-Strong Labels In Audio Event Classification](https://mlsanity.com/paper/2105.07031/) (2021)
- [Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering](https://mlsanity.com/paper/2503.11197/) (2025)
- [CochlScene: Acquisition of acoustic scene data using crowdsourcing](https://mlsanity.com/paper/2211.02289/) (2022)
- [Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning](https://mlsanity.com/paper/2309.11500/) (2023)
- [CED: Consistent ensemble distillation for audio tagging](https://mlsanity.com/paper/2308.11957/) (2023)
- [AudioTime: A Temporally-aligned Audio-text Benchmark Dataset](https://mlsanity.com/paper/2407.02857/) (2024)
- [OpenMU: Your Swiss Army Knife for Music Understanding](https://mlsanity.com/paper/2410.15573/) (2024)
- [FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion](https://mlsanity.com/paper/2506.01111/) (2025)

## Abstract (arXiv)

Large Audio Language Models (LALMs) still struggle in complex acoustic scenes because they often fail to preserve task-relevant acoustic evidence before reasoning begins. We identify this error pattern as the evidence bottleneck: state-of-the-art systems show larger deficits in acoustic evidence extraction than in downstream reasoning, suggesting that upstream perception is often the limiting factor. To address this problem, we propose EvA (Evidence-First Audio), a dual-path architecture that enhances acoustic evidence preservation through hierarchical aggregation and non-compressive, time-aligned fusion. We also build EvA-Perception, a large-scale training set with about 54K event-ordered captions and 500K evidence-grounded QA pairs. Under a unified zero-shot protocol, EvA achieves the best open-source Perception results on MMAU, MMAR, and MMSU, with the largest gains on perception-heavy splits. Human evaluation on open-ended captioning further shows improved fine-grained acoustic coverage and caption quality. These results support the evidence-first hypothesis: stronger audio understanding depends on preserving acoustic evidence before reasoning. Project can be found at https://satsuki2486441738.github.io/EvA/.