Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval

• URL: http://arxiv.org/abs/2604.23734v1
• Date: Sun, 26 Apr 2026 14:28:48 GMT
• Title: Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval
• Abstract summary: We introduce Prism-Reranker, a family of reranker models built on Qwen3.5 at four sizes (0.8B, 2B, 4B, 9B)<n>In addition to the standard yes/no relevance judgement, whenever the verdict is yes the model emits a contribution statement summarizing how the document helps the query.<n>We show that the same recipe extends existing LLM-based rerankers, augmenting Qwen3-Reranker-4B with contribution and evidence capabilities.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Modern retrieval pipelines increasingly serve downstream consumers like retrieval-augmented generation (RAG) and autonomous agents that need more than a scalar relevance score. A reranker that only tells the caller "how relevant" forces the agent to dump entire documents into the language-model context, wasting tokens on tangential passages and boilerplate. We introduce Prism-Reranker, a family of reranker models built on Qwen3.5 at four sizes (0.8B, 2B, 4B, 9B) that goes beyond scalar scoring. In addition to the standard yes/no relevance judgement, whenever the verdict is yes the model emits (i) a contribution statement summarizing how the document helps the query, and (ii) an evidence passage: a self-contained rewrite that preserves every query-relevant signal while discarding noise. Prism-Reranker is trained with a hybrid objective combining point-wise distillation from a strong commercial reranker API with supervised fine-tuning on contribution and evidence targets. We curate training data from KaLM-Embedding's open-source aggregation, augmented with real web documents retrieved via commercial search APIs for open-domain queries and LLM-synthesized variants, and rewrite a portion of queries into keyword-style reformulations to adapt the model to agent-issued traffic. To reconcile inconsistent labels across open corpora and obtain crisp binary supervision, we relabel data with an LLM-as-Judge ensemble aggregating votes from five frontier LLMs. On a QA subset of BEIR and on an LLM-judged evaluation of contribution and evidence quality, Prism-Reranker attains solid results across all four sizes. We further show that the same recipe extends existing LLM-based rerankers, augmenting Qwen3-Reranker-4B with contribution and evidence capabilities while improving its average BEIR-QA NDCG@10 by +1.54 over the base model. Model weights, training recipe, and evaluation suite are released.

Related papers

• Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation [51.55755193937205]
  We propose QREAM, a style-controlled rewriter that aligns retrieved documents with a question-oriented style while preserving facts.<n>Our framework consists of two stages: (1) QREAM-ICL, which uses stylistic seeds to guide iterative rewriting exploration; and (2) QREAM-FT, a lightweight student model distilled from denoised ICL outputs.
  arXiv  Detail & Related papers  (2026-04-19T08:39:21Z)
• One Model Is Enough: Native Retrieval Embeddings from LLM Agent Hidden States [5.647839536820347]
  This paper introduces a lightweight projection head that maps hidden states directly into the embedding space, eliminating the need for a separate embedding model.<n> Experiments on the QReCC conversational search benchmark show competitive Recall@10 and MRR@10 compared to the standard generate-then-encode pipeline.
  arXiv  Detail & Related papers  (2026-03-09T14:25:35Z)
• RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline [9.49236542025774]
  We propose RECAP, an agentic pipeline designed to elicit and verify memorized training data from large language models.<n>At the heart of RECAP is a feedback-driven loop, where an initial extraction attempt is evaluated by a secondary language model.<n>We evaluate RECAP on EchoTrace, a new benchmark spanning over 30 full books, and the results show that RECAP leads to substantial gains over single-iteration approaches.
  arXiv  Detail & Related papers  (2025-10-29T20:36:37Z)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation [96.18720164390699]
  This paper explores the use of large language models (LLMs) for annotating document utility in training retrieval and retrieval-augmented generation (RAG) systems.<n>Our results show that LLM-generated annotations enhance out-of-domain retrieval performance and improve RAG outcomes compared to models trained solely on human annotations or downstream QA metrics.
  arXiv  Detail & Related papers  (2025-04-07T16:05:52Z)
• Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning [76.50690734636477]
  We introduce Rank-R1, a novel LLM-based reranker that performs reasoning over both the user query and candidate documents before performing the ranking task.<n>Our experiments on the TREC DL and BRIGHT datasets show that Rank-R1 is highly effective, especially for complex queries.
  arXiv  Detail & Related papers  (2025-03-08T03:14:26Z)
• Multi-Facet Blending for Faceted Query-by-Example Retrieval [5.156059061769101]
  We propose a multi-facet blending (FaBle) augmentation method, which exploits modularity by decomposing and recomposing to explicitly synthesize facet-specific training sets.<n>Our modularization eliminates the need for pre-defined facet knowledge or labels.<n>FaBle augmentation on 1K documents remarkably assists training in obtaining facet conditional embeddings.
  arXiv  Detail & Related papers  (2024-12-02T12:32:19Z)
• Contrastive Learning to Improve Retrieval for Real-world Fact Checking [84.57583869042791]
  We present Contrastive Fact-Checking Reranker (CFR), an improved retriever for fact-checking complex claims. We leverage the AVeriTeC dataset, which annotates subquestions for claims with human written answers from evidence documents. We find a 6% improvement in veracity classification accuracy on the dataset.
  arXiv  Detail & Related papers  (2024-10-07T00:09:50Z)
• MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models [22.50450558103786]
  In a real-world RAG system, the current query often involves spoken ellipses and ambiguous references from dialogue contexts.<n>We propose a novel query rewriting method MaFeRw, which improves RAG performance by integrating multi-aspect feedback from both the retrieval process and generated results.<n> Experimental results on two conversational RAG datasets demonstrate that MaFeRw achieves superior generation metrics and more stable training compared to baselines.
  arXiv  Detail & Related papers  (2024-08-30T07:57:30Z)
• CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation [76.31621715032558]
  Grounded generation aims to equip language models (LMs) with the ability to produce more credible and accountable responses. We introduce CaLM, a novel verification framework. Our framework empowers smaller LMs, which rely less on parametric memory, to validate the output of larger LMs.
  arXiv  Detail & Related papers  (2024-06-08T06:04:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.