Question Answering

Also known as QA

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 28% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 165

All topics

Domain Fine-Tuning vs. Retrieval-Augmented Generation for Medical Multiple-Choice Question Answering: A Controlled Comparison at the 4B-Parameter Scale
Apr 26, 2026Avi-ad Avraam BuskilaRetrieval-Augmented Generation Healthcare
Department of Information Science and Applied Artificial Intelligence, Bar-Ilan University, Ramat-Gan, Israel
Evaluating Large Language Models on Computer Science University Exams in Data Structures
Apr 25, 2026Edan Gabay, Yael Maoz, Jonathan Stahl +7LLM Evaluation Computer Science Education
Blavatnik School of Computer Science and AI
EverydayGPT: Confidence-Gated Routing for Efficient and Safe Hybrid GPT-RAG Conversational QA
Apr 24, 2026Jaspreet Singh NahalLLM Inference Efficiency Retrieval-Augmented Generation
B.Tech Computer Science Engineering (Artificial Intelligence) Dr. A.P.J. Abdul Kalam Technical University, Delhi, India
CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems
Apr 24, 2026Tabinda Sarwar, Farhad Moghimifar, Cong Duy Vu Hoang +6Question Answering Text-to-SQL
Oracle Corporation
STRIDE: Strategic Iterative Decision-Making for Retrieval-Augmented Multi-Hop Question Answering
Apr 19, 2026Wei Chen, Lili Zhao, Zhi Zheng +2Multi-Hop QA Self-Training for Language Models
University of Science and Technology of China & State Key Laboratory of Cognitive Intelligence Hefei, Anhui, China · NIO Hefei, Anhui, China
BAGEL: Benchmarking Animal Knowledge Expertise in Language Models
Apr 17, 2026Jiacheng Shen, Masato Hagiwara, Milad Alizadeh +9LLM Evaluation Question Answering
2NYU Center for Data Science; NYU Shanghai · 1Earth Species Project · 3NYU Shanghai Center for Data Science; NYU-ECNU Institute of Mathematical Sciences at NYU Shanghai
DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answering
Apr 16, 2026Neha Srikanth, Jordan Boyd-Graber, Rachel RudingerQuestion Answering
University of Maryland
CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factors
Apr 16, 2026Hang Su, Zequn Liu, Chen Hu +3LLM Personalization Question Answering
East China Normal University, China · Zhongguancun Academy, China
Spatial Atlas: Compute-Grounded Reasoning for Spatial-Aware Research Agent Benchmarks
Apr 13, 2026Arun SharmaSpatial Reasoning Benchmarks Question Answering
University of Minnesota, Twin Cities
Indirect Question Answering in English, German and Bavarian: A Challenging Task for High- and Low-Resource Languages Alike
Mar 16, 2026Miriam Winkler, Verena Blaschke, Barbara PlankQuestion Answering Multilingual QA
UMaiNLP lab, Center for Information and Language Processing, LMU Munich, Germany · ÆMunich Center for Machine Learning, Germany
Agentic Very Long Video Understanding
Jan 26, 2026Aniket Rege, Arka Sadhu, Yuliang Li +5Question Answering Egocentric Video Understanding
Reality Labs Research at Meta · University of Wisconsin-Madison · Work done during internship at Meta
OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models
Nov 30, 2025Michael Siebenmann, Javier Argota Sánchez-Vaquerizo, Stefan Arisona +3Question Answering Agentic RAG
Professorship of Computational Social Science, ETH Zurich, 8092 Zürich, Switzerland · Esri R&D Center Zurich, 8005 Zürich, Switzerland · Complexity Science Hub, Vienna, 1030, Austria
HarmReduction: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs
Jul 29, 2025Kaixuan Wang, Chenxin Diao, Jason T. Jacques +2Healthcare Question Answering
University of Oxford, United Kingdom · University of Edinburgh, United Kingdom · University of St Andrews, United Kingdom +1
Popular but Wrong: Understanding and Mitigating LLM Overconfidence through Knowledge Popularity
May 23, 2025Shiyu Ni, Keping Bi, Jiafeng Guo +1LLM Hallucination Mitigation Confidence Estimation in Language Models
CAS Key Lab of Network Data Science and Technology, ICT, CAS · State Key Laboratory of AI Safety · University of Chinese Academy of Sciences
QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL
Jun 15, 2024Yinggang Sun, Ziming Guo, Haining Yu +5Synthetic Data Generation Question Answering
School of Cyberspace Science · Harbin Institute of Technology · Harbin, China +4

Apr 26, 2026, cs.CLJ/K move · Enter open · S save

Domain Fine-Tuning vs. Retrieval-Augmented Generation for Medical Multiple-Choice Question Answering: A Controlled Comparison at the 4B-Parameter Scale

Avi-ad Avraam Buskila

Department of Information Science and Applied Artificial Intelligence, Bar-Ilan University, Ramat-Gan, Israel

Retrieval-Augmented Generation Healthcare LLM Fine-Tuning Question Answering Medical QA RAG Evaluation

Open paper AskPDF arXiv

Practitioners deploying small open-weight large language models (LLMs) for medical question answering face a recurring design choice: invest in a domain-fine-tuned model, or keep a general-purpose model and inject domain knowledge at inference time via retrieval-augmented generation (RAG). We isolate this trade-off by holding model size, prompt template, decoding temperature, retrieval pipeline, and evaluation protocol fixed, and varying only (i) whether the model has been domain-adapted (Gemma 3 4B vs. MedGemma 4B, both 4-bit quantized and served via Ollama) and (ii) whether retrieved passages from a medical knowledge corpus are inserted into the prompt. We evaluate all four cells of this 2x2 design on the full MedQA-USMLE 4-option test split (1,273 questions) with three repetitions per question (15,276 LLM calls). Domain fine-tuning yields a +6.8 percentage-point gain in majority-vote accuracy over the general 4B baseline (53.3% vs. 46.4%, McNemar p < 10^-4). RAG over MedMCQA explanations does not produce a statistically significant gain in either model, and in the domain-tuned model the point estimate is slightly negative (-1.9 pp, p = 0.16). At this scale and on this benchmark, domain knowledge encoded in weights dominates domain knowledge supplied in context. We release the full experiment code and JSONL traces to support replication.

Momentum

Related topics

Latest papers 165