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

arXiv:2609.16912v1 Announce Type: new 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.

Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA
BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering
An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA
UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering
CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering

Source: arXiv cs.CL | 2026-09-16

Related