Rebol: Retrieval Via Bayesian Optimization With Batched LLM Relevance Observations And Query Reformulation
2026 · Anton Korikov, Scott Sanner
Abstract
LLM-reranking is limited by the top-k documents retrieved by vector similarity, which neither enables contextual query-document token interactions nor captures multimodal relevance distributions. While LLM query reformulation attempts to improve recall by generating improved or additional queries, it is still followed by vector similarity retrieval. We thus propose to address these top-k retrieval stage failures by introducing ReBOL, which 1) uses LLM query reformulations to initialize a multimodal Bayesian Optimization (BO) posterior over document relevance, and 2) iteratively acquires document batches for LLM query-document relevance scoring followed by posterior updates to optimize relevance. After exploring query reformulation and document batch diversification techniques, we evaluate ReBOL against LLM reranker baselines on five BEIR datasets and using two LLMs (Gemini-2.5-Flash-Lite, GPT-5.2). ReBOL consistently achieves higher recall and competitive rankings, for example compared
Authors
(none)
Tags
Stats
Related papers
- Corank: Llm-based Compact Reranking With Document Features For Scientific Retrieval (2025)0.00
- Supervised Fine-tuning Or Contrastive Learning? Towards Better Multimodal LLM Reranking (2025)0.00
- Refit: Relevance Feedback From A Reranker During Inference (2023)0.00
- DS@GT At TREC TOT 2025: Bridging Vague Recollection With Fusion Retrieval And Learned Reranking (2026)0.00
- Promptreps: Prompting Large Language Models To Generate Dense And Sparse Representations For Zero-shot Document Retrieval (2024)10.61
- Bixse: Improving Dense Retrieval Via Probabilistic Graded Relevance Distillation (2025)0.00
- Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52
- Formalized Information Needs Improve Large-language-model Relevance Judgments (2026)0.00