{"ID":2839062,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.16326","arxiv_id":"2511.16326","title":"ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning","abstract":"Retrieval-Augmented Generation (RAG) has emerged as a powerful framework for knowledge-intensive tasks, yet its effectiveness in long-context scenarios is often bottlenecked by the retriever's inability to distinguish sparse yet crucial evidence. Standard retrievers, optimized for query-document similarity, frequently fail to align with the downstream goal of generating a precise answer. To bridge this gap, we propose a novel fine-tuning framework that optimizes the retriever for Answer Alignment. Specifically, we first identify high-quality positive chunks by evaluating their sufficiency to generate the correct answer. We then employ a curriculum-based contrastive learning scheme to fine-tune the retriever. This curriculum leverages LLM-constructed Knowledge Graphs (KGs) to generate augmented queries, which in turn mine progressively challenging hard negatives. This process trains the retriever to distinguish the answer-sufficient positive chunks from these nuanced distractors, enhancing its generalization. Extensive experiments on 10 datasets from the Ultradomain and LongBench benchmarks demonstrate that our fine-tuned retriever achieves state-of-the-art performance, improving 14.5\\% over the base model without substantial architectural modifications and maintaining strong efficiency for long-context RAG. Our work presents a robust and effective methodology for building truly answer-centric retrievers. Source Code is available on https://github.com/valleysprings/ARK/.","short_abstract":"Retrieval-Augmented Generation (RAG) has emerged as a powerful framework for knowledge-intensive tasks, yet its effectiveness in long-context scenarios is often bottlenecked by the retriever's inability to distinguish sparse yet crucial evidence. Standard retrievers, optimized for query-document similarity, frequently...","url_abs":"https://arxiv.org/abs/2511.16326","url_pdf":"https://arxiv.org/pdf/2511.16326v3","authors":"[\"Hang Ding\",\"Jiawei Zhou\",\"Haiyun Jiang\"]","published":"2025-11-20T13:05:09Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"RAG\",\"Large Language Model\"]","has_code":false,"code_links":[{"ID":606840,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839062,"paper_url":"https://arxiv.org/abs/2511.16326","paper_title":"ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning","repo_url":"https://github.com/valleysprings/ARK","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}