Interactive Audio Eval

Evaluates Large Audio Models (LAMs) on real-world, task-oriented voice assistant interactions by capturing user preferences through open-ended pairwise comparisons. It measures how well models align with actual user needs and preferences in an interactive setting, rather than relying on static reference-based benchmarks. Use when the user wants to benchmark on TalkArena Interactive User Preferences, or asks about evaluating this task. Reports Bradley-Terry model score.

qhjqhj00 66087f1 3.4 KB Updated 3 repo stars

File contents

qhjqhj00/research-skills-pool/tree/main/skill-factory/output/interactive-audio-eval commit 66087f1bd5

Frequently asked questions

npx skillmds add qhjqhj00/interactive-audio-eval