Latest Question Answering Research Papers

The newest Question Answering papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Question Answering so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
  Pedro Carvalho Brom · arXiv · Oct 29, 2026

  Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…

• IndicIPR-QA: A Benchmark for Extractive Question Answering on Indian IPR Laws
  M. Mohaiminul Islam, Muhammad Abulaish · arXiv · Oct 29, 2026

  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. How…

• Neighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering
  Mesut Ceylan, Arda Baris Basaran, Elgar Fleisch, Filipe Barata · arXiv · Oct 29, 2026

  Large language models (LLMs) are increasingly capable, yet they produce wrong answers indistinguishable from correct ones. In question answering (QA), such an error propagates unnoticed into downstream tasks. Perturbation-based uncertainty …

• Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation
  Yi Wang, Tianzi Wang, Peter Bell · arXiv · Oct 28, 2026

  Fine-grained audio-visual question answering (AVQA) requires models to resolve complex cross-modal correspondences and temporally grounding from sparsely distributed evidence. Omni-modal agents, which autonomously orchestrate perception too…

• Latent Visual Contrastive Reasoning with Multi-Branch Exploration
  Kegeng Tang, Jingbo Wang, Yangming Zhang, Huanshu Zhang et al. · arXiv · Oct 27, 2026

  Multimodal large language models have made substantial progress in visual question answering, but complex visual reasoning often requires locating and comparing multiple pieces of question-relevant visual evidence. Existing methods that mov…

• DocSkill: Skill-Integrated Agentic Reasoning for Multilingual Multi-Hop Document Question Answering
  Jing Huang, Zhiya Tan, Changtao Miao, Shutao Gong et al. · arXiv · Oct 27, 2026

  Multilingual multi-hop document question answering (MMHop-DocQA) requires locating and integrating evidence across complex layouts, document pages, and diverse languages. Existing approaches include single-pass processing and adaptive tool …

• Not One Belief: Answer Payloads, Persistence, and Dissociated Confidence Signals in Conversational Question Answering
  Duc-Vinh Tran · arXiv · Oct 26, 2026

  Conversational QA systems should fix errors when users push back and signal which answers to trust. We split each follow-up into its speech act (re-ask, agree, or challenge) and its payload (an answer string, correct or not), and measure fo…

• EXCISE: Locating and Excising Distracting Sentences in Medical Question Answering
  Yerim Hong, Sohyun Son, Heeseung Chung, Mujeen Sung · arXiv · Oct 26, 2026

  Language models are increasingly considered for clinical decision support, where their answers should be grounded in clinical evidence and remain robust to irrelevant information. Prior work shows that a single irrelevant sentence can lower…

• Improving VLMs on Scientific Chart Analysis via Autonomous Evolution
  Abhinav Sudhakar Dubey, Vidushi Goel, Kiran Rana, Shikhar Mathur et al. · arXiv · Oct 26, 2026

  Understanding and operating with scientific charts is a standard approach in data analysis, and while humans are good at interpreting such charts, open vision-language models (VLMs) are known to perform poorly when it comes to question answ…

• ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning
  Rhea Sanjay Sukthanker, Pashmina Cameron · arXiv · Oct 26, 2026

  Reasoning language models generate thousands of tokens per answer, and generation speed is limited by memory bandwidth, so storing weights in two bits instead of bfloat16 can potentially make inference 8$\times$ cheaper. Two-bit methods are…

• On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
  Leon Sick, Lukas Hoyer, Yannick Strümpler, Christian Reisswig et al. · arXiv · Oct 23, 2026

  On-policy self-distillation enables post-training foundation models without relying on stronger external teachers. However, existing approaches rely on ground-truth question-answer pairs, human-curated problem sets, or other supervised sign…

• When is more search useful? An Empirical Study of Search Utility in Quality-Aware Decoding for Machine Translation
  Javier Garcia Gilabert, Rico Sennrich, André F. T. Martins · arXiv · Oct 23, 2026

  Quality-Aware Decoding (QAD) improves machine translation through test-time scaling, generating multiple candidate translations and selecting the final output with a quality-aware decoder. Usually the same candidate budget N is spent on eve…

• Reading Between the Layers: Cross-Modal Alignment and Representational Hierarchy in Vision Transformers
  Sugam Karki, Raúl Vázquez, Yova Kementchedjhieva · arXiv · Oct 23, 2026

  While large vision-language models excel at optical character recognition, it remains unclear how their underlying vision encoders process text and its meaning, and whether they support anything resembling reading comprehension. We systemat…

• Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images
  Somraj Gautam, Gaurav Harit · arXiv · Oct 23, 2026

  Recent advances in Vision-Language Models (VLMs) have significantly improved Visual Question Answering (VQA) performance, yet their reasoning over structured content such as tables remains inconsistent, often plagued by spatial misalignment…

• Collection-Date Assignment Redirects Answers in Temporal QA
  Minsu Oh, Seunghui Jwa, Soo Kyun Kim, Yeo-Chan Yoon · arXiv · Oct 23, 2026

  A collection date records when a source revision was acquired, not when its contents changed. Can assigning this metadata redirect temporal question answering despite unchanged evidence? Swapping the question day and following day between t…

• Disentangling Question, Response, and Verifier Languages in Multilingual P(True) Self-Evaluation
  Jewon Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park et al. · arXiv · Oct 23, 2026

  When a language model is asked whether its own answer is correct, three languages are involved: that of the question, that requested for the answer, and that of the verifier instruction asking for the judgment. Multilingual confidence evalu…

• SQuAT: Spherical Lattice Vector Quantization-Aware Training
  Sebastian Loeschcke, Ivan Koryakovskiy, Tycho F. A. van der Ouderaa, Riccardo Del Chiaro et al. · arXiv · Oct 22, 2026

  Vector quantization (VQ), in particular lattice-based methods, offer strong rate-distortion trade-offs for low-bit large language models (LLMs), yet their behavior under quantization-aware training (VQ-QAT) remains poorly understood. We sca…

• IndoNutriQA: An Indonesian Clinical Nutrition Question Answering Benchmark
  Tirana Noor Fatyanosa, Ummu Ditya Erliana, Mahendra Data, Muhammad Nurwegiono et al. · arXiv · Oct 22, 2026

  Clinical Question Answering (QA) underpins Clinical Intelligent Decision Support Systems, but progress is severely limited for low-resource languages such as Indonesian by the absence of public domain-specific data. We introduce IndoNutriQA…

• Prompt Sensitivity in Tool-Augmented Model Comparisons
  Mateusz Modrzejewski, Tomasz Radzikowski · arXiv · Oct 22, 2026

  Language models are compared on question-answering benchmarks that pose each question in one wording, and a reworded question can change which of two models scores higher. We ask whether giving the models tools makes such comparisons more s…

• Mixing Matters: Evidence Position Bias Across Sequence Mixers in Long-Context Question Answering
  Aman Behera, Namit Solanki, Mehul Anand · arXiv · Oct 22, 2026

  Long-context models often use answer-bearing evidence less effectively when it appears away from a prompt boundary. We compare this position bias across Transformer, state-space, and hybrid Mamba architectures by moving one gold document th…

• Silicon Samples Match the Answers but Not the Respondents
  Yusuke Kumagae, Masahiro Kaneko · arXiv · Oct 22, 2026

  Silicon sampling generates survey respondents by having a large language model (LLM) answer a survey as a person with given demographic attributes, and the resulting synthetic populations are increasingly used in place of human ones. Existi…

• CulturalRiddles: A Multicultural Benchmark of Riddles
  My Chiffon Nguyen, Tianyi Hu, Vinod Anbalagan, Henry Gagnier et al. · arXiv · Oct 21, 2026

  As LLMs expand their language coverage, evaluating how well they understand and represent diverse cultures becomes increasingly important. However, many benchmarks remain English-centric, with limited cultural coverage and a focus on factua…

• Graph Topology Meets Energy-Driven Pathfinding: Preserving Contextual Consistency in Retrieval-Augmented Generation
  Yufeng Li, Zaijing Li, Fuchen Zhang, Zongzong Wu et al. · arXiv · Oct 21, 2026

  Retrieval-augmented generation (RAG) frequently integrates knowledge graphs (KGs) for complex multi-hop question answering. However, their performance is increasingly bottlenecked by the knowledge structuring and reasoning processes. (i) Se…

• Task-Preserving Multilingual Instruction Tuning for Open-Ended QA in WMT 2026 MIST
  Aleix Sant, Jordi Luque, Carlos Escolano · arXiv · Oct 21, 2026

  This paper describes our submission to the WMT 2026 Multilingual Instruction Shared Task. We adapt Qwen3-8B with LoRA using organiser-provided data, EuroAlpaca, a multilingual instruction dataset created through task-preserving localisation…

• Effects of Model Scale and Quantization on Social Bias and Abstention in Question Answering
  Kuniko Paxton, Ifeoluwa Wuraola, Dhavalkumar Thakker · arXiv · Oct 21, 2026

  The deployment of small and quantized language models in resource-constrained settings raises an important fairness question: when a compressed model produces fewer biased responses, does this reflect fairer behavior or greater abstention? …

• Corpus Quality Improves, Retrieval Utility Does Not: An Ablation of Preprocessing and Refinement in a Speech-to-QA Pipeline
  Wonsup Shin, Jingu Kim · arXiv · Oct 20, 2026

  Practitioners building training corpora with a pipeline of language models keep a preprocessing or refinement (post-process) stage when switching it on raises the corpus quality. We ablate a production pipeline that turns conference speech …

• KEEP-Bench: Evaluating Evidence Preservation in Context Compression
  Ziqing Man, Di Wu, Jia-Chen Gu, Junyi Zhang et al. · arXiv · Oct 19, 2026

  Context compression improves long-context efficiency but may introduce faithfulness issues through an information bottleneck. Existing evaluations rely on QA metrics, but a reader can still answer correctly from an unfaithful compression, s…

• SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?
  Zhaoxi Zhang, Hao Liang, Linxuan Wu, Yiming Wu et al. · arXiv · Oct 19, 2026

  Spatial intelligence requires agents to actively acquire visual evidence and integrate observations into a coherent representation of the three-dimensional world. Yet spatial question answering offers limited evidence of whether models can …

• Self-Consistency of Entity Sets and Citations in a Deep Research System under Repeated Prompting
  Lauri Pykälä, Kimmo K. Kaski · arXiv · Oct 19, 2026

  Deep research agents (DRA) are commonly used for open-ended synthesis tasks where closed-world QA benchmarks are poorly suited to characterize relevant aspects of performance. We study the self-consistency of one commercial deep research sy…

• How Benchmark Graph Construction Shapes Multi-Hop KG Navigation: A Controlled Audit of PathQuestion and PathQuestion-Large
  Eduin E. Hernandez, Sergio A. Diaz, Luis F. Garcia, Nurassyl Askar et al. · arXiv · Oct 19, 2026

  Multi-hop knowledge-graph question answering (KGQA) benchmarks are often treated as fixed language-and-reasoning tasks, but for navigation-based methods, difficulty also depends on the graph in which those tasks are instantiated. This makes…