Metraipolis › archive › dc_d255b68987d4
Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature — arXiv:2609.16912
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16912
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T19:19:23.158Z
- SHA-256 of the archived text
38b56ff2d5f10fd57caa02e9b89e050c82769768696ef2dff64a5b8c4937c140- Stable URL of this page
https://metraipolis.com/documento/dc_d255b68987d4
How to cite
Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature — arXiv:2609.16912 — arXiv (en), https://arxiv.org/abs/2609.16912 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d255b68987d4 (Metraipolis archive dc_d255b68987d4, sha256 38b56ff2d5f10fd57caa02e9b89e050c82769768696ef2dff64a5b8c4937c140)
BibTeX
@misc{dcd255b68987d4,
title = {Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature — arXiv:2609.16912},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16912},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d255b68987d4; sha256 38b56ff2d5f10fd57caa02e9b89e050c82769768696ef2dff64a5b8c4937c140},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16912. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.16912 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T18:32:32.843Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).