{"ID":3083858,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T03:54:17.966829144Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05812","arxiv_id":"2606.05812","title":"FORTE: FOL-guided Optimal Refinement for Text-audio rEtrieval","abstract":"Text-to-audio retrieval has made significant progress with shared embedding models such as CLAP and Pengi, yet they often struggle with fine-grained semantic alignment due to the inherent modality gap between text and audio. In this work, we propose FORTE, a unified framework that integrates structured logical reasoning with parameter-efficient cross-modal alignment to improve retrieval precision. Our approach first transforms queries into first-order logic and refines them via a constrained search that preserves semantic invariance while introducing discriminative attributes. The refined representation is then aligned with audio embeddings using a lightweight projection module, followed by a predicate-aware re-ranking step that enforces logical consistency at inference. Extensive experiments on AudioCaps and Clotho demonstrate consistent improvements over strong baselines, particularly in challenging fine-grained scenarios. Our results highlight the effectiveness of combining symbolic reasoning with representation learning for cross-modal retrieval.","short_abstract":"Text-to-audio retrieval has made significant progress with shared embedding models such as CLAP and Pengi, yet they often struggle with fine-grained semantic alignment due to the inherent modality gap between text and audio. In this work, we propose FORTE, a unified framework that integrates structured logical reasonin...","url_abs":"https://arxiv.org/abs/2606.05812","url_pdf":"https://arxiv.org/pdf/2606.05812v1","authors":"[\"Arghya Pal\",\"Sailaja Rajanala\"]","published":"2026-06-04T07:50:33Z","proceeding":"cs.MM","tasks":"[\"cs.MM\",\"eess.AS\"]","methods":"[]","has_code":false}