arXiv Computation and Language September 16, 2026 By Akira Ise, Kotaro Kumagai, Yuta Yamaguchi, Hisanori Ozaki, Yukio Uematsu, Ikuya Yamada

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

Read the original on arXiv Computation and Language →

Lit3R is a system developed by tus-nlp for the LitTraceQA shared task, which focuses on evidence-grounded question answering over scientific literature. The system combines off-the-shelf retrieval, reranking, and large language model components without task-specific training, using an iterative retrieval process that merges BM25-based sparse and dense retrieval, cross-encoder reranking, and LLM verification, along with paper-to-paper expansion. In the official test set, Lit3R achieved a 4th place ranking on the leaderboard.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Aug 5

SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG

arXiv:2608. 03860v1 Announce Type: cross Abstract: We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19.

By Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab, Asab Azad

rag nlp benchmarks

arXiv AI

Jul 28

VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy

arXiv:2607. 23006v1 Announce Type: cross Abstract: Scientific question answering requires a retrieval system to solve two distinct problems: identifying which papers are relevant and locating the supporting evidence within those papers.

By Xinyan Zhong, Yuwei Shi, Yuqi Wei, Chen Shen, Tianhang Zhou, Zhenghao Wu

llms rag agents nlp benchmarks

arXiv AI

Sep 2

EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Language Models

The paper introduces EGT-KG, an evidence‑grounded typed knowledge graph retrieval framework designed to enhance scientific question answering with small language models (SLMs). It compares three QA settings—standard Retrieval‑Augmented Generation (RAG) and two EGT‑KG variants (automatically generated and expert‑defined relation schemas)—using a six‑dimensional evaluation on a biopolymer‑bound soil composite literature benchmark. Results show that both EGT‑KG variants outperform vanilla RAG, with the llama3:8b model achieving a final score of 70.37 (+14.67%) and 68.82 (+12.14%) for the AS and ES variants, respectively.

By Muran Yu, Jiechao Gao, Yuandong Pan, Barney H. Miao, Andrew C. Lesh, Kincho H. Law, Jie Wang, Michael D. Lepech

llms rag benchmarks safety

arXiv AI

Aug 18

What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering

arXiv:2608. 14841v1 Announce Type: new Abstract: Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines.

By Guanchen Wu, Jiayuan Ding, Subhabrata Mukherjee, Carl Yang

llms nlp multimodal

arXiv AI

Jun 30

Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?

arXiv:2606. 28367v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval.

By Sadanand Singh, Allam Reddy, Manan Chopra

rag nlp benchmarks

arXiv Computation and Language

Aug 28

RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature

RATIO (Retrieval Across Typed Ideation Operations) is a large-scale benchmark designed to evaluate how well retrieval systems can support scientific inspiration. It defines relevance through three ideation moves—Address, Broaden, and Specify—each targeting different levels of abstraction in literature retrieval. The benchmark is built from millions of full-text CS papers using a novel discourse-marker distant supervision method, and includes extensive LLM and human vetting to ensure quality.

By Maayan Sharon, Tom Hope

llms fine-tuning benchmarks

One email a morning, machine-written

Related stories

SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG

VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy

EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Language Models

What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering

Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?

RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature