arXiv AI September 2, 2026 By Muran Yu, Jiechao Gao, Yuandong Pan, Barney H. Miao, Andrew C. Lesh, Kincho H. Law, Jie Wang, Michael D. Lepech

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

Read the original on arXiv AI →

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.

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 AI.

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 Computation and Language

3d ago

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

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.

By Akira Ise, Kotaro Kumagai, Yuta Yamaguchi, Hisanori Ozaki, Yukio Uematsu, Ikuya Yamada

llms rag nlp benchmarks

arXiv AI

Aug 24

EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering

arXiv:2608.21252v1 Announce Type: cross Abstract: Question answering (QA) over long, connected documents remains challenging because relevant evidence may span multiple entities and their relationshi...

By Xuanyu Meng, Jiashuo Sun, Jash Rajesh Parekh, Jiawei Han

llms rag nlp

arXiv AI

3d ago

AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research

arXiv:2609.16519v1 Announce Type: new Abstract: Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that...

By Bernie Boscoe, Srinath Saikrishnan, Vikram Seenivasan, Jack Stark, Andrew Lizarraga, Morgan Himes, Jonathan Soriano, PJ Allen, Tuan Do

llms rag benchmarks safety data-engineering

arXiv AI

Jul 29

Multimodal Hybrid Retrieval-Augmented Generation for Scientific Document Understanding using Open-Source SLMs

arXiv:2607. 24799v1 Announce Type: cross Abstract: Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning.

By Alexandru-Andrei Sauc\u{a}, Ana-Luiza Rusnac

llms rag fine-tuning multimodal benchmarks

arXiv AI

4d ago

Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain

The paper evaluates seven open‑source large language models for retrieval‑augmented generation in the ESG reporting domain, using 498 real‑world ESG reports from EU‑listed companies and 100 synthetic QA pairs. Performance is measured with RAGAS metrics, showing strong retrieval scores but variable generation quality, especially in faithfulness and factual correctness. The results highlight significant differences across model architectures and underscore the need for domain‑specific fine‑tuning to improve factual accuracy.

By Motaz Saad, Anna Borrelli, Ivan Gentile, Kianna Kazemi, Francesco Piccialli, Antonella Longo

llms rag fine-tuning

One email a morning, machine-written

Related stories

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

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

EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering

AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research

Multimodal Hybrid Retrieval-Augmented Generation for Scientific Document Understanding using Open-Source SLMs

Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain