Scientific QA

QA: Question Answering

Scientific question answering studies how AI can answer questions about research literature, scientific data, and technical subjects in ways that are accurate and verifiable. Common approaches combine retrieval-augmented generation with sparse and dense search, reranking, citation checks, and structured representations such as knowledge graphs; multimodal systems also interpret figures, tables, and other scientific documents. Benchmarks increasingly test multi-hop reasoning, quantitative tasks, evidence location, citation quality, and whether systems abstain when answers are unsupported. A central challenge is that fluent answers and strong aggregate scores do not guarantee faithful use of evidence, especially when questions require synthesis across sources or modalities.

Latest papers

63 papers14 papers in the last four weeks, up 40% on the four weeks before. 0.1% of all new papers.

A Domain-Aware Pipeline for Structured Extraction and Retrieval-Augmented Question Answering over arXiv Superconductivity Literature
Oct 25, 2026Ivan Iorsh, Aleksandr Kapitonov, Ivan Filianin +2Scientific Document Retrieval Scientific QA
ITMO University, Saint Petersburg, Russia · New Uzbekistan University, Tashkent, Uzbekistan
MuninAI: A Self-Hosted Agentic Framework for Independent Research Groups
Oct 16, 2026Markus Fischer, Jens Meiler, Matthias ElgetiScientific QA Agentic RAG
Institute for Drug Discovery, Leipzig University Medical School, Leipzig, Germany · Institute for Medical Physics and Biophysics, Leipzig University Medical School, Leipzig, Germany · Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Dresden/Leipzig, Germany +3
Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for Agents
Oct 15, 2026Yutong Leng, Haojiong Chen, Fukai Shang +4Knowledge Representation KG Construction
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University
ChemExplain: A Multimodal Benchmark for Explanatory Chemical Reasoning
Oct 12, 2026Aotian Chen, Frazier N. Baker, Reza Averly +5Scientific Reasoning Explainability Evaluation
The Ohio State University · Adelaide University
Arctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic Science
Oct 7, 2026Benjamin Wilcox, Dawei Gao, Pradeeban Kathiravelu +3LLM Abstention LLM Evaluation
University of North Texas, Denton, TX · University of Alaska Anchorage, Anchorage, AK
Leveraging a four-quadrant approach for evaluating Redpine Science
Oct 6, 2026Filip Dorm, Leonora VesterbackaScientific QA RAG Evaluation
Redpine, Sweden.
From Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models
Oct 5, 2026Qiuhui Chen, Yibo Liu, Tao Dai +3Knowledge Augmentation for Language Models Scientific QA
School of Information Science and Engineering, East China University of Science and Technology · School of Computer Science, Shanghai Jiao Tong University · Tencent
Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists
Oct 4, 2026Kate Zhang, Yuante LiAI Agent Evaluation Scientific Agent Benchmarks
School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213
PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation
Sep 30, 2026Rashid Azraf Jahin, Saadman Sajid, Khan Raiyan Ibne Reza +1Benchmark Design Scientific QA
Dept. of Electrical and Computer Engineering North South University Dhaka, Bangladesh
TRACE: Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction for LitTraceQA
Sep 30, 2026Sachin Gupta, Divya GodaraScientific QA Evidence Retrieval
Independent Researcher San Jose, USA
PathAnchor: Path-Structured Evidence for Scientific Agents
Sep 30, 2026Qiuhui Chen, Jiafan Lu, Shuaimin Tang +5Evidence-Grounded Reasoning Scientific QA
School of Information Science and Engineering, East China University of Science and Technology · College of Intelligent Robotics and Advanced Manufacturing, Fudan University · Tencent
Where Scientific Search Agents Fail: Decision-Checkpoint Auditing of Exposure and Inspection Attempts
Sep 29, 2026Hongmin Li, Wanli ZhaoAI Agent Auditing Scientific QA
School of Life Science and Technology, Institute of Science Tokyo Tokyo, Japan · Department of Computational Biology and Medical Sciences Graduate School of Frontier Sciences, The University of Tokyo Kashiwa, Japan · Department of Information Science Graduate School of Advanced Science and Engineering, Hiroshima University Higashihiroshima, Japan
Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering
Sep 29, 2026Bhagyesh Rathi, Eshan Chawla, William B. AndreopoulosLate Interaction Retrieval Scientific QA
San Jose State University, Department of Computer Science
AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Scientific Question Answering
Sep 28, 2026Chanhee Park, Jeongho Yoon, Sungbin Han +2Multi-Hop QA Tool-Augmented Language Model Agents
Korea University · Sookmyung Women’s University
Large Knowledge Model: A Knowledge Foundation for Agentic Science at Scale
Sep 23, 2026Yuan Huang, Sihan Hu, Hongyu Gu +18KG Construction AI Agents for Scientific Discovery
DP Technology, Beijing, China · Institute of Theoretical Physics, Chinese Academy of Sciences, Beijing, China · International Center for Quantum Materials, School of Physics, Peking University, Beijing, China +4
PageRecall: Measuring Page Selection in Literature-Grounded Question Answering
Sep 16, 2026Aaditya ChauhanDocument Information Extraction Scientific QA
Independent Researcher
Rethinking Domain Specialization for Open-Ended Scientific Reasoning in Astronomy Language Models
Sep 15, 2026Vanessa Lama, Sanjay Das, Emily Herron +5LLM Evaluation Scientific QA
Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA · The Ohio State University, Columbus, Ohio, USA · Max-Planck-Institut für Astronomie, Königstuhl 17, D-69117 Heidelberg, Germany +1
BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific Reasoning in Physics-Grounded Biological Research
Sep 15, 2026Qingyang XuEvidence-Grounded Reasoning Scientific Reasoning in Language Models
Independent Researcher Shanghai, China
Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature
Sep 15, 2026Akira Ise, Kotaro Kumagai, Yuta Yamaguchi +3Scientific QA Evidence-Grounded Generation
♠Tokyo University of Science · ♣Dentsu Soken Inc. · ♡Studio Ousia
AstroSpecLM: A Spectrum-Language Model for Evidence-Grounded Astronomical Spectral Analysis
Sep 7, 2026Jinghang Shi, Yanxia Zhang, Ali Luo +2Language Modeling Scientific QA
Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks
Sep 7, 2026Timothy KassisPrompt Engineering LLM Agent Evaluation
K-Dense
SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding
Sep 4, 2026Shenxi Wu, Yuhong Liu, Haosong Zhang +8Document Understanding LLM Evaluation
The Chinese University of Hong Kong · Shanghai Artificial Intelligence Laboratory · New York University +5
From Terminology to Diagrams: Visual-Instruction Generation for Scientific Diagram Understanding
Sep 1, 2026Raul Ortega, José Manuel Gómez-PérezVisual Question Answering Scientific QA
Language Technology Research Laboratory Expert.ai 17 Henri Dunant, 28036 Madrid, Spain
EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Language Models
Aug 31, 2026Muran Yu, Jiechao Gao, Yuandong Pan +5Knowledge Graphs Small Language Models
Department of Civil and Environmental Engineering, Stanford University · Department of Civil Engineering, University of Calgary
HANIA: Planner-Guided Multimodal Graph Evidence Selection for Grounded Question Answering
Aug 29, 2026Zafar Ali, Asad Khan, Nimbeshaho Thierry +3Multimodal QA Multimodal Reasoning
School of Computer Science and Engineering, Southeast University, Nanjing, China · Portland Institute Nanjing, NJUPT, Nanjing, China · School of Information Science and Engineering, Shandong University, Qingdao, China +1
GRACE: Grounded Reasoning via Adapter Composition and Evidence-Aware Calibration for Educational Visual Question Answering
Aug 19, 2026Xinjin Li, Yudi Xia, Xi Zhao +8Visual Question Answering VLM Adaptation
Columbia University, New York, NY, USA · Independent Researcher · Carnegie Mellon University, Pittsburgh, PA, USA +6
LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering
Aug 7, 2026Xuye Liu, Yimu Wang, Peng Shi +7Evidence-Grounded Generation Scientific QA
University of Waterloo · 2Amazon · 3City University of Hong Kong +1
SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG
Aug 4, 2026Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab +1Cross-Encoder Reranking Scientific QA
Laurentian University · North South University
EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents
Jul 30, 2026Luigi Sigillo, Matteo Silvestri, Francesco Tabaro +9LLM Agent Orchestration Scientific QA
1EMBL Rome, European Molecular Biology Laboratory, Monterotondo, Italy. · 3Sapienza University of Rome, Italy. · 2European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK. +3
SciDataSailor: Deep Scientific Data Exploring
Jul 29, 2026Jiyong Rao, Yicheng Qiu, Chi Zhang +2Scientific QA AI Agent Benchmarks
Shanghai Artificial Intelligence Laboratory · Tongji University

Oct 25, 2026J/K move · Enter open · S save

A Domain-Aware Pipeline for Structured Extraction and Retrieval-Augmented Question Answering over arXiv Superconductivity Literature

Ivan Iorsh, Aleksandr Kapitonov, Ivan Filianin, Matvey Lesonen+1

ITMO University, Saint Petersburg, Russia · New Uzbekistan University, Tashkent, Uzbekistan

Scientific Document Retrieval Scientific QA Retrieval-Augmented Generation Hybrid Retrieval Materials Science

Open paper AskPDF arXiv

Scientific literature in materials physics is growing faster than researchers can manually inspect it, yet most retrieval tools rely on keyword matching or generic question answering that ignores domain-specific structure in PDF files. This paper presents an end-to-end pipeline that transforms arXiv superconductivity publications into a searchable corpus with structured metadata and retrieval-augmented question answering. The system combines thematic corpus construction, domain-aware extraction of materials and superconducting transition temperatures, and hybrid retrieval that merges dense chunk embeddings with structured publication fields. We test whether normalized domain attributes improve evidence retrieval and answer groundedness relative to lexical-only and dense text-only methods. Extraction is evaluated on a manually verified gold set of 59 superconducting materials, 46 of which have confirmed experimental critical temperatures. On the 33-material primary positive subset, domain-aware pair accuracy reaches 45.5% versus 9.1% for a regex baseline. Retrieval and generation are compared under a fixed language model (qwen2.5:7b-instruct) on a 100-question benchmark, varying only the retrieval mechanism: BM25, dense, hybrid, and hybrid with domain metadata. BM25 gives the highest source recall (Recall@5 of 47%), and adding extracted metadata to hybrid retrieval does not improve it (39% versus 41%), which we attribute to noise in the extracted fields; the main bottleneck is locating the supporting span inside a correctly retrieved paper. As a materials-informatics application, literature-derived temperatures are matched to an independent theoretical reference set: 200 materials appear in both sources, and 20 have a median experimental critical temperature above the theoretical value.