Open-Domain QA

QA: Question Answering

Ask about this topic

Overview

Open-domain question answering studies how to answer questions when the relevant facts may come from broad text collections, the web, or visual environments rather than a fixed knowledge base. Systems combine sparse or dense retrieval, retrieval-augmented generation, and iterative search agents to gather evidence, then synthesize answers, often across multiple documents. Current approaches also use reinforcement learning, synthetic training data, and evidence-based rubrics, while evaluation spans factual benchmarks such as PopQA and EntityQuestions and open-ended settings that assess grounding and detail. A central tension is that retrieval can improve factual coverage but also adds latency and noisy evidence, making selective search, reliable synthesis, and calibrated uncertainty important open problems.

Latest papers

CardsList

19 papers3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. Task-Preserving Multilingual Instruction Tuning for Open-Ended QA in WMT 2026 MIST

    Oct 21, 2026Aleix Sant, Jordi Luque, Carlos EscolanoMultilingual QAFine-Tuning Language Models

    Scientific Research, Telefónica Innovación Digital · Universitat Politècnica de Catalunya

  2. Learning to Program Retrievals: Composing Search Primitives via Reinforcement Learning

    Oct 17, 2026Kyuyoung Kim, Zilin Xiao, Zhiyuan Wang +4Retrieval-Augmented ReasoningRL for RAG

    KAIST AI · Meta Superintelligence Labs

  3. Bridging Semantic Gaps in RAG through Generated Context Knowledge Fusion

    Sep 29, 2026Xinkai Du, Chao Lv, Yalin Sun +3Retrieval-Augmented GenerationSemantic Search

    Beijing Wanlian Zhilian Technology Corporation Limited, Beijing, China · Department of Computer Science and Technology, Tsinghua University, Beijing, China · Sunshine Digital Intelligence Tech Co., Ltd., Beijing, China

  4. Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images

    Sep 27, 2026Kaname Kitamura, Asako KanezakiEmbodied QAOpen-Domain QA

    Department of Computer Science, Institute of Science Tokyo, Tokyo, Japan · RIKEN, Japan · Tohoku University, Sendai, Japan

  5. Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG

    Sep 4, 2026Shuyu Guo, Shuo Zhang, Zhaochun RenRL for RAGLLM Inference Acceleration

    Shandong University Qingdao, China · Bloomberg London, United Kingdom · Leiden University Leiden, The Netherlands

  6. From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers

    Aug 24, 2026Aman Saini, Priyanshu Kumar, Eric Peng +3Open-Domain QAReward Modeling

    Apple

  7. DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering

    Aug 19, 2026Xujia Wang, Yizhe Zhang, Bin Xu +2Evidence-Grounded GenerationEvidence-Grounded QA

    Department of Computer Science and Technology, Tsinghua University

  8. Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering

    Aug 18, 2026Hsiang-Wei Huang, Fu-Chen Chen, Li-Wu Tsao +7Embodied QA3D VQA

    University of Washington, United States · Amazon, United States · The University of Texas at Austin, United States

  9. Diversity is Not Ambiguity: Toward Accurate and Efficient Ambiguity Detection for Open-Domain QA

    Aug 4, 2026Jiwon Lee, Yong-chan Park, Jungin Hong +1Question AnsweringOpen-Domain QA

    Seoul National University

  10. EviBack: Search-Agent Reinforcement Learning via Evidence-Constrained Teacher Backoff

    Jul 27, 2026Xiao Ma, Zhiquan Hu, Yi Wei +5Reinforcement LearningAgentic RAG

    NEXTAI Research Institute, Chery Group

  11. BLUEX v2: Benchmarking LLMs on Open-Ended Questions from Brazilian University Entrance Exams

    Jun 21, 2026João Guilherme Alves Santos, Giovana Kerche Bonás, Thiago Laitz +2Multilingual Language Model EvaluationLLM Evaluation

    University of Campinas (UNICAMP), Campinas-SP, Brazil · Tropic AI, Campinas-SP, Brazil · Maritaca AI, Campinas-SP, Brazil

  12. CAPF: Guiding Search-Agent Rollouts with Credit-Attenuated Privileged Feedback

    Jun 1, 2026Bin Chen, Xinye Liao, Yiming Liu +2RL for Language Model ReasoningCredit Assignment in RL

  13. SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks

    May 29, 2026Wai-Chung Kwan, Aryo Pradipta Gema, Joshua Ong Jun Leang +1Open-Ended GenerationSelf-Play RL

    University of Edinburgh · Imperial College London

  14. EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA

    May 27, 2026Yunsheng Zeng, Gen Li, Yuwei Miao +8RL for Language ModelsReinforcement Learning with Verifiable Rewards

    1Baidu Inc.

  15. MiRD: Reliable Set-Valued Prediction for Open-Ended Question Answering via Miscoverage Risk Decomposition

    May 25, 2026Anqi Hu, Zhiyuan Wang, Zijun Jia +1LLM Hallucination MitigationSet Prediction

    University of Electronic Science and Technology of China · Beihang University

  16. Predicting the Benefit of Retrieval Augmentation in Open-Domain Question Answering

    Apr 9, 2026Or Dado, David Carmel, Oren KurlandRetrieval-Augmented GenerationAdaptive RAG

    Technion, Haifa, Israel · Technology Innovation Institute (TII), Haifa, Israel

  17. TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs

    Mar 11, 2026Yutao Xie, Nathaniel Thomas, Nicklas Hansen +3RL for Language Model ReasoningReward Shaping

    UC San Diego · AWS AI

  18. LiCQA : A Lightweight Complex Question Answering System

    Feb 25, 2026Sourav Saha, Dwaipayan Roy, Mandar MitraQuestion AnsweringOpen-Domain QA

    Indian Statistical Institute, Kolkata, India · Indian Institute of Science Education and Research, Kolkata, India

  19. RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering

    Feb 19, 2026Yiming Zhang, Siyue Zhang, Junbo Zhao +1Dense RetrievalOpen-Domain QA

    Zhejiang University · Nanyang Technological University · NYU Shanghai +1