{"ID":6620453,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12290","arxiv_id":"2607.12290","title":"The Sound of Absence: Audio-Language Embedding Models Struggle with Negation","abstract":"Audio-language embedding models such as CLAP are widely evaluated on matching present sound events, but rarely on negation. We show this affirmation-only evaluation hides a key limitation: these models fail to encode negated sound concepts, mapping affirmative and negated captions to nearly identical representations. To expose this blind spot, we introduce NegEval-Audio, a framework that converts existing datasets into two negation-aware tasks, Retrieval-Neg and Multiple-Choice Negation (MCQ-Neg), to probe whether models distinguish present from absent events. On AudioCaps and Clotho, performance degrades sharply under negation, with negation-type MCQ accuracy falling far below chance, and the failure persists even for a recent multimodal LLM-based embedding model. While a training-free steering method improves MCQ-Neg, it yields marginal gains for Retrieval-Neg. This indicates that affirmation bias is a fundamental flaw in the representation geometry, necessitating explicit negation-aware training objectives.","short_abstract":"Audio-language embedding models such as CLAP are widely evaluated on matching present sound events, but rarely on negation. We show this affirmation-only evaluation hides a key limitation: these models fail to encode negated sound concepts, mapping affirmative and negated captions to nearly identical representations. T...","url_abs":"https://arxiv.org/abs/2607.12290","url_pdf":"https://arxiv.org/pdf/2607.12290v1","authors":"[\"Chun-Yi Kuan\",\"Hung-yi Lee\"]","published":"2026-07-14T02:55:00Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.AI\",\"cs.CL\",\"cs.LG\",\"cs.SD\"]","methods":"[\"Large Language Model\"]","has_code":false}