AudioICL-Bench: A Benchmark for Large Audio Language Model In-Context Learning
TL;DR
AudioICL-Bench is introduced, a diagnostic benchmark whose per-episode rules are resampled so that no correct answer is recoverable from prior knowledge, and its nine tasks are organized along two axes that separate what must be learned from demonstrations from what must be perceived in the signal, enabling failures to be attributed to either source.
Abstract
In-context learning (ICL) promises training-free adaptation for audio, where labeling every new condition is costly. Yet existing audio ICL studies largely measure Task Recognition, where demonstrations merely cue pre-trained capabilities, rather than Task Learning, where a genuinely new input-label mapping must be inferred from demonstrations alone. We introduce AudioICL-Bench, a diagnostic benchmark whose per-episode rules are resampled so that no correct answer is recoverable from prior knowledge. Its nine tasks are organized along two axes that separate what must be learned from demonstrations from what must be perceived in the signal, enabling failures to be attributed to either source. Across five Large Audio Language Models, the strongest models readily bind arbitrary sounds to new labels when perception is easy, but collapse on temporal measurement and composing multiple induced rules, revealing two primary capability boundaries: temporal perception and multi-rule composition.