# A Sensitivity Analysis of Multi-Event Audio Grounding in Audio LLMs

arXiv: https://arxiv.org/abs/2603.03855 · HTML: https://mlsanity.com/paper/2603.03855/

## Key facts

- Cited by 2 papers in the map (data through 19 Oct 2026).
- First posted on arXiv 4 Mar 2026.

## Built on by (most cited first, 2 of 2)

- [TAG-Bench: Benchmarking Temporal Audio Grounding in Large Audio Language Models](https://mlsanity.com/paper/2609.01542/) (2026)
- [RefTAG: Reflection-aware Temporal Audio Grounding in Large Audio Language Models](https://mlsanity.com/paper/2610.16217/) (2026)

## Abstract (arXiv)

Audio LLMs have shown a strong ability to understand audio samples, yet their reliability in complex acoustic scenes remains under-explored. Unlike prior work limited to small scale or less controlled query construction, we present a large-scale evaluation of event grounding and false alarms as auditory scene complexity increases. Using 71K AudioCapsV2 clips, we extract normalized (source, attribute) events and build two query types: present-event queries for ground-truth detection and absent-event queries to probe hallucinations, using similarity-filtered negative sampling in an audio-aligned text embedding space. We evaluate four SOTA Audio LLMs with 12 prompt variants over 500K yes/no queries per model. Across models, increasing event count consistently lowers true-positive rate and raises false-positive rate, while prompts induce a strong trade-off between the two. Our confidence analysis shows that models become more uncertain on multi-event audio, revealing room for improvement.