Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature

• URL: http://arxiv.org/abs/2609.16912v1
• Date: Tue, 15 Sep 2026 09:50:15 GMT
• Title: Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature
• Abstract summary: We describe tus-nlp's Lit3R (Retrieve-Relate-Read) system for LitTraceQA.<n>Lit3R combines off-the-shelf retrieval, reranking, and large language model (LLM) components without task-specific training.<n>The reader first identifies supporting evidence within individual papers and then synthesizes evidence across papers to produce the final answer and evidence trace.
• Score: 4.514081720659125
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We describe tus-nlp's Lit3R (Retrieve-Relate-Read) system for LitTraceQA, a shared task for literature-grounded question answering that requires systems to retrieve relevant papers, identify supporting evidence, and generate answers. Lit3R combines off-the-shelf retrieval, reranking, and large language model (LLM) components without task-specific training. The retriever iteratively combines BM25-based sparse and dense retrieval, cross-encoder reranking, and LLM-based verification, and complements retrieval based on the question with paper-to-paper expansion. The reader first identifies supporting evidence within individual papers and then synthesizes evidence across papers to produce the final answer and evidence trace. On the official test set, our system ranked 4th on the leaderboard. Our code is available at https://github.com/tus-ist-nlp/littraceqa.

Related papers

• LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering [30.616598264585203]
  We present LitTraceQA, a benchmark for literature-grounded question answering over scientific papers.<n>Given a research question and a metadata pool of papers, a system must return three connected outputs.<n>We analyze a larger final annotation collection with 4,978 unique-question records over 4,859 unique gold papers.
  arXiv  Detail & Related papers  (2026-08-07T16:11:52Z)
• ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning [78.94047086588078]
  We propose Recursive Evidence as LLM Harness for Long-Context Reasoning.<n>It is a training-free inference method for improving long-context reasoning.<n> Experiments on eight long-context datasets with 128K context length show it consistently improves evidence utilization.
  arXiv  Detail & Related papers  (2026-07-02T17:59:26Z)
• ACL-Verbatim: hallucination-free question answering for research [1.1852769462463206]
  We apply the extractive question answering system VerbatimRAG to research papers in the ACL Anthology.<n>We contribute a novel ground truth dataset for the task of mapping user queries to relevant text spans in research papers.<n>Human annotation is performed by NLP researchers and is based on synthetic user queries generated using a custom pipeline.
  arXiv  Detail & Related papers  (2026-05-20T12:30:29Z)
• IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review [10.586701795115609]
  IntrAgent is designed to mimic human behaviors when reading literature for information retrieval.<n>It identifies relevant sections and then iteratively extracting key details to refine the retrieved information.<n>IntrAgent achieves 13.2% higher cross-domain accuracy than state-of-the-art RAG and research-agent baselines.
  arXiv  Detail & Related papers  (2026-04-23T01:55:08Z)
• VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification [107.75781898355562]
  We introduce a novel framework, called VeriCite, designed to rigorously validate supporting evidence and enhance answer attribution.<n>We conduct experiments across five open-source LLMs and four datasets, demonstrating that VeriCite can significantly improve citation quality while maintaining the correctness of the answers.
  arXiv  Detail & Related papers  (2025-10-13T13:38:54Z)
• LitSearch: A Retrieval Benchmark for Scientific Literature Search [48.593157851171526]
  We introduce LitSearch, a retrieval benchmark comprising 597 realistic literature search queries about recent ML and NLP papers. All LitSearch questions were manually examined or edited by experts to ensure high quality. We find a significant performance gap between BM25 and state-of-the-art dense retrievers, with a 24.8% absolute difference in recall@5.
  arXiv  Detail & Related papers  (2024-07-10T18:00:03Z)
• Attribute or Abstain: Large Language Models as Long Document Assistants [58.32043134560244]
  LLMs can help humans working with long documents, but are known to hallucinate. Existing approaches to attribution have only been evaluated in RAG settings, where the initial retrieval confounds LLM performance. This is crucially different from the long document setting, where retrieval is not needed, but could help. We present LAB, a benchmark of 6 diverse long document tasks with attribution, and experiments with different approaches to attribution on 5 LLMs of different sizes.
  arXiv  Detail & Related papers  (2024-07-10T16:16:02Z)
• LLatrieval: LLM-Verified Retrieval for Verifiable Generation [67.93134176912477]
  Verifiable generation aims to let the large language model (LLM) generate text with supporting documents. We propose LLatrieval (Large Language Model Verified Retrieval), where the LLM updates the retrieval result until it verifies that the retrieved documents can sufficiently support answering the question. Experiments show that LLatrieval significantly outperforms extensive baselines and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2023-11-14T01:38:02Z)
• Query Rewriting for Retrieval-Augmented Large Language Models [139.242907155883]
  Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs.
  arXiv  Detail & Related papers  (2023-05-23T17:27:50Z)
• Visconde: Multi-document QA with GPT-3 and Neural Reranking [4.9069311006119865]
  This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple documents. The system, called Visconde, uses a three-step pipeline to perform the task: decompose, retrieve, and aggregate.
  arXiv  Detail & Related papers  (2022-12-19T17:39:07Z)
• Generate rather than Retrieve: Large Language Models are Strong Context Generators [74.87021992611672]
  We present a novel perspective for solving knowledge-intensive tasks by replacing document retrievers with large language model generators. We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
  arXiv  Detail & Related papers  (2022-09-21T01:30:59Z)

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.