GRAPE: Let GPRO Supervise Query Rewriting By Ranking For Retrieval

Abstract

The CLIP model has become a cornerstone of large-scale retrieval systems by aligning text and image data in a unified embedding space. Despite its simplicity and efficiency, CLIP struggles when applied to tasks whose input distributions diverge from its training corpus, such as queries with multilingual, long-form, or multimodal differences. To avoid costly retraining, existing methods mainly adopt query-rewriting strategies with large language models (LLMs), aiming to mitigate distribution gaps at the query level. However, due to the lack of supervision signals, LLMs fail to generate the optimal one that fits the training distribution. We address this challenge with GRAPE (Grouped Ranking-Aware Policy Optimization Enhancement), a plug-and-play enhancement approach that incorporates ranking signals into retrieval-guided query rewriting with LLMs. Intuitively, GRAPE proposes to leverage GRPO to bridge distributional differences -- including length, multilingual, and modality shifts -- b

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2025grape

Related papers

• Domain-aware RAG: Mol-enhanced RL For Efficient Training And Scalable Retrieval (2025)0.00
• Expandr: Teaching Dense Retrievers Beyond Queries With LLM Guidance (2025)3.25
• Pseudo Relevance Feedback Is Enough To Close The Gap Between Small And Large Dense Retrieval Models (2025)0.00
• Region-r1: Reinforcing Query-side Region Cropping For Multi-modal Re-ranking (2026)0.00
• Generalized Contrastive Learning For Multi-modal Retrieval And Ranking (2024)6.01
• Learning To Rank In Generative Retrieval (2023)11.91
• CGPT: Cluster-guided Partial Tables With Llm-generated Supervision For Table Retrieval (2026)1.57
• What Drives Cross-lingual Ranking? Retrieval Approaches With Multilingual Language Models (2025)0.00