GRM: Generative Relevance Modeling Using Relevance-Aware Sample Estimation for Document Retrieval
Recent studies show that Generative Relevance Feedback (GRF), using text generated by Large Language Models (LLMs), can enhance the effectiveness of query expansion. However, LLMs can generate irrelevant information that harms retrieval effectiveness. To address this, we propose Generative Relevance Modeling (GRM) that uses Relevance-Aware Sample Estimation (RASE) for more accurate weighting of expansion terms. Specifically, we identify similar real documents for each generated document and use a neural re-ranker to estimate their relevance. Experiments on three standard document ranking benchmarks show that GRM improves MAP by 6-9% and R@1k by 2-4%, surpassing previous methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Document RankingRetrievalSimilar Papers 제목 키워드 기반
Boosting LLM-based Relevance Modeling with Distribution-Aware Robust Learning
With the rapid advancement of pre-trained large language models (LLMs), recent endeavors have leveraged the capabilities of LLMs in relevance modeling, resulting in enhanced performance. This is usually done through the …
Out of Distribution (OOD) DetectionUniGD: A Unified Generative-Discriminative Framework for Industrial Retrieval
Generative retrieval (GR) is a promising paradigm for industrial search advertising, yet its deployment is constrained by strict relevance and latency requirements. Existing systems cascade GR with an independent relevan…
ADORE: Autonomous Domain-Oriented Relevance Engine for E-commerce
Relevance modeling in e-commerce search remains challenged by semantic gaps in term-matching methods (e.g., BM25) and neural models' reliance on the scarcity of domain-specific hard samples. We propose ADORE, a self-sust…
Knowledge DistillationCTR-Guided Generative Query Suggestion in Conversational Search
Generating effective query suggestions in conversational search requires aligning model outputs with user preferences, which is challenging due to sparse and noisy click signals. We propose GQS, a generative framework th…
Conversational SearchDiversityOptimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search
Ranking relevance is a fundamental task in search engines, aiming to identify the items most relevant to a given user query. Traditional relevance models typically produce scalar scores or directly predict relevance labe…
Reinforcement Learning