Question Answering

Also known as QA

Question answering asks how systems can find, interpret, and combine information to answer questions, from short factual queries to multi-hop reasoning over documents, conversations, images, video, and structured data. Common approaches include retrieval-augmented generation, fine-tuning, knowledge graphs, tool-using agents, and symbolic methods; evaluations span reading comprehension, open-domain and long-document QA, conversational QA, and specialized domains. Current work also focuses on multilingual and multimodal settings, personalization, and recognizing when to clarify or abstain rather than guess. A central tension is that better retrieval or reasoning does not always produce more reliable answers: systems must still handle missing or conflicting evidence, avoid hallucinations, and balance accuracy, coverage, latency, and cost.

Latest papers

263 papers28 papers in the last four weeks, down 20% on the four weeks before. 0.2% of all new papers.

IndicIPR-QA: A Benchmark for Extractive Question Answering on Indian IPR Laws
Oct 29, 2026M. Mohaiminul Islam, Muhammad AbulaishQuestion Answering Legal QA
Department of Computer Science and Engineering, South Asian University, New Delhi, India
Neighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering
Oct 29, 2026Mesut Ceylan, Arda Baris Basaran, Elgar Fleisch +1Uncertainty Quantification LLM Uncertainty Estimation
ETH Zurich, Zurich, Switzerland · University of St.Gallen, St.Gallen, Switzerland
Benchmarking decision models against generative large language models on medical multiple-choice questions
Oct 28, 2026Oscar Freyer, Daniel Glauert, Moritz Hofmann +3LLM Evaluation Clinical Language Model Evaluation
Else Kröner Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany · Independent researcher, Berlin, Germany · Denkmal.ai, Berlin, Germany +2
Rethinking Retrieval in the Long-Context Era: Training-Free Semantic Trees for Adaptive Context Construction
Oct 25, 2026Zhe Xu, Tianhao Liao, Zhenqing Ling +3Long-Context Retrieval Information Retrieval
Sun Yat-sen University · Alibaba Group
Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
Oct 22, 2026Zhengye Bao, Shengtao Zhang, Haokai Zhang +3Conversational QA Memory Management for LLM Agents
Luo Lab Undergraduate Division (LUD), Xi’an Jiaotong University · Shanghai Jiao Tong University · Zhejiang University +1
Before the Ticket: Grounding HPC User Support in Documentation and Resolved Tickets with an Agentic LLM Assistant
Oct 21, 2026Elham J. Barezi, Primus C Kabuo, Niveditha NerellaQuestion Answering Document QA
Rosen Center for Advanced Computing, Purdue University, West Lafayette, IN, USA
Accept or Repair: Preserving Passage-Supported Answers in Contrastive Decoding
Oct 21, 2026Jungseob Lee, Seungyoon Lee, Hyeonseok Moon +6Evidence-Grounded QA Language Model Decoding
Korea University · Sookmyung Women’s University · Yonsei University Mirae Campus +2
Effects of Model Scale and Quantization on Social Bias and Abstention in Question Answering
Oct 21, 2026Kuniko Paxton, Ifeoluwa Wuraola, Dhavalkumar ThakkerSocial Bias in Language Models Language Model Bias Evaluation
University of Hull Cottingham Road, Hull, HU6 7RX, United Kingdom
MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records
Oct 20, 2026Seohyun Lee, Jongha Kim, Dohwan Ko +4Enterprise AI Agents Question Answering
KAIST, Daejeon, Republic of Korea · Korea University, Seoul, Republic of Korea
Benchmark for Structured Retrieval-Augmented Generation in Perovskite Photovoltaics
Oct 18, 2026Qiwei Han, Chi Zhou, Gaoxiang YuanStructured RAG RAG Evaluation
Department of Chemistry, Duke University, Durham, NC 27708, USA · Department of Computer Science, Georgia Institute of Technology, Atlanta, GA 30332, USA · Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY 11201, USA
Acharya 2.0: An AI Tutor for Self-Learning Subjects in Hindi
Oct 18, 2026Shantipriya Parida, Debasish Dhal, Sonal Khosla +2Educational QA Intelligent Tutoring Systems
AMD Silo AI, Finland · Odia Generative AI, India
Toward Agentic Retrieval-Augmented Generation for Enterprise Retail Workflows over Heterogeneous Data Sources
Oct 18, 2026Jeonghwan Choi, Jibin Hwang, Hayoon Park +2Agentic RAG RAG Evaluation
Korea Advanced Institute of Science and Technology (KAIST) · GS Retail · Cluvion
DKnown-Jev: Fine-Tuning and Evaluation of a JEV-Style Model for Tasks Involving Normative Knowledge
Oct 17, 2026Qi Li, Jianjun Xu, Pingtao WeiLLM Fine-Tuning LLM Evaluation
Beijing Caizhi Tech, Beijing, China
Beyond the Answer: Student-Conditioned Trace Construction for Reasoning Distillation
Oct 16, 2026Shaoang Li, Yanhang Shi, Yufei Li +6CoT Distillation Question Answering
Stony Brook University · Meta AI
Content associations with answer selection and engagement in supply chain community question answering
Oct 15, 2026Hisatoshi NaganawaQuestion Answering
International Maritime Research Center, Kobe University, Kobe, Japan
ListQA: A Benchmark for Evaluating List-Formatted Factual Knowledge Retrieval in Large Language Models
Oct 13, 2026Mayank Kulkarni, Rakesh VaideeswaranFactual QA Factual Knowledge in Language Models
Amazon AGI
Strong yet Controllable LLM Abstention without Learning to Abstain
Oct 12, 2026Junwei Zhang, Yifei Wang, Wanli Yang +6Factual QA LLM Abstention
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences · Beijing Institute of Technology
Test-Time Memory Construction
Oct 9, 2026Zijun Wang, Yifan Ji, Haidong Xin +6Conversational QA Memory-Augmented Language Models
School of Computer Science and Engineering, Northeastern University, China · Department of Computer Science and Technology, Tsinghua University, China · Alibaba Group, China
COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering
Oct 9, 2026Kavinda Kehelella, Sanghamitra DuttaLanguage Model Distillation Knowledge Distillation
University of Maryland, College Park
GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports
Oct 8, 2026Veronika Solopova, Ivan Havlytskyi, Viktoria Skorik +1Question Answering Document QA
RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees
Oct 8, 2026Meghanadh Pulivarthi, Swaraj Kumar Biswal, Kushagra Bhushan +3Retrieval-Augmented Generation Structured RAG
IBM · IIT Kharagpur
Right Number, Wrong State? Measuring Cross-Jurisdiction Substitution in LLM Recall of State Policy
Oct 7, 2026Jiayu FengLLM Reliability Question Answering
Harvard T.H. Chan School of Public Health
Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering
Oct 5, 2026Aditya Tanna, Abhishek JindalReward Modeling RL for Language Model Reasoning
Dhirubhai Ambani University Gandhinagar, Gujarat, India
Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents
Oct 1, 2026Ahmad Yehia, Aly O. Abdelkareem, Islam Ahmed +4LLM Agent Memory Persistent Memory for Language Models
The University of Texas at Austin · AIDAChip Inc.
Distilling Directional Verification
Oct 1, 2026Jungseob Lee, Sugyeong Eo, Seongtae Hong +4Factual QA Question Answering
Korea University · Yonsei University Mirae Campus · Soongsil University +1
SEPAL: Separated Expert Pairs with Answer-Level Fusion for Reliable LLM Collaboration
Sep 30, 2026Weijie Ren, Yanwen Zhang, Hao Li +3Multi-Agent LLM Systems Question Answering
Zhejiang University · University of Electronic Science and Technology of China · University of Science and Technology of China
When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning
Sep 30, 2026Yunbei Zhang, Janet Wang, Jihun Hamm +1Visual Reasoning Question Answering
Tulane University · Virginia Tech
Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
Sep 29, 2026Hui Ren, Lei Fan, Henry Pao +5Multimodal Memory Question Answering
University of Illinois Urbana-Champaign · Amazon.com, Inc.
Learning to Retrieve Missing Evidence for Long-Term Memory QA
Sep 29, 2026Yi-Xuan Deng, Yi Zhang, Wei Liu +2Long-Term Conversational Memory Evidence Retrieval
Tsinghua University
Memory in the Sky: Low-Altitude Question Answering with Multi-Agent Memory Aggregation
Sep 28, 2026Chengyang Li, Yujie Wan, Shuai Wang +6Question Answering Multi-Agent Systems
The University of Hong Kong, Hong Kong SAR, China · Southern University of Science and Technology, Shenzhen, China · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China +2

Oct 29, 2026J/K move · Enter open · S save

IndicIPR-QA: A Benchmark for Extractive Question Answering on Indian IPR Laws

M. Mohaiminul Islam, Muhammad Abulaish

Department of Computer Science and Engineering, South Asian University, New Delhi, India

Question Answering Legal QA Legal NLP

Open paper AskPDF arXiv

Legal Question Answering (QA) over statutory texts is a challenging task in Natural Language Processing (NLP), especially in low-resource settings with complex legal systems. It requires answers that are precise and grounded in the law. However, to the best of current knowledge, no existing extractive QA benchmark provides exact answer spans from statutory texts across all seven Indian Intellectual Property Rights (IPR) Acts. This paper presents IndicIPR-QA1, an extractive QA benchmark for Indian IPR laws. The proposed dataset contains 4,462 QA pairs from 1,116 statutory contexts across seven Acts. Questions and answers are generated using GPT-4o and validated through nine automatic quality checks, single and multi-model LLM evaluations, and a 200-pair human audit. Section-level partitioning prevents source-context overlap across the training, validation, and test sets. Further analysis examines answer span length, lexical overlap, and multi-clause structure across the corpus and individual Acts. BM25 achieves a token-level F1 score of 20.21, while fine-tuned InLegalBERT reaches 85.02 under a unified sliding-window inference protocol. The large performance gap between BM25 (20.21 F1) and InLegalBERT (85.02 F1) shows that simple word matching is not enough to answer these legal questions. Performance also varies across the seven Acts, indicating substantial differences in answer-extraction performance.