List your company
ResearchFormerly WizWand

Research

Papers for “question answering”

Find papers, implementations, and the benchmark evidence behind state-of-the-art AI systems.

TitleAuthorsYearSource
MUST-VQA: MUltilingual Scene-text VQAEmanuele Vivoli, Ali Furkan Biten, Andres Mafla2022arxiv 2209.06730
Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge GraphsElan Markowitz, Anil Ramakrishna, Jwala Dhamala2024arxiv 2407.21358
MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention HeadsWeihao Liu, Ning Wu, Shiping Yang2025arxiv 2502.13963
An Evaluation of GPT-4V and Gemini in Online VQAMengchen Liu, Chongyan Chen, Danna Gurari2023arxiv 2312.10637
VideoOFA: Two-Stage Pre-Training for Video-to-Text GenerationXilun Chen, Lili Yu, Wenhan Xiong2023arxiv 2305.03204
PaLI-X: On Scaling up a Multilingual Vision and Language ModelXi Chen, Josip Djolonga, Piotr Padlewski2023arxiv 2305.18565
Hierarchical Memory for Long Video QAYiqin Wang, Haoji Zhang, Yansong Tang2024arxiv 2407.00603
Comparative Analysis of Neural QA models on SQuADSoumya Wadhwa, Khyathi Raghavi Chandu, Eric Nyberg2018arxiv 1806.06972
ReadTwice: Reading Very Large Documents with MemoriesYury Zemlyanskiy, Joshua Ainslie, Michiel de Jong2021arxiv 2105.04241
Improving QA Efficiency with DistilBERT: Fine-Tuning and Inference on mobile Intel CPUsNgeyen Yinkfu2025arxiv 2505.22937
Enhancing the QA Model through a Multi-domain Debiasing FrameworkYuefeng Wang, ChangJae Lee2026arxiv 2601.11581
Spoken Conversational Search for General KnowledgeLina M. Rojas-Barahona, Pascal Bellec, Benoit Besset2019arxiv 1909.11980
TalentMine: LLM-Based Extraction and Question-Answering from Multimodal Talent TablesVarun Mannam, Fang Wang, Chaochun Liu2025arxiv 2507.00041
Towards Faithful and Robust LLM Specialists for Evidence-Based Question-AnsweringTobias Schimanski, Jingwei Ni, Mathias Kraus2024arxiv 2402.08277
AQuA: Automated Question-Answering in Software Tutorial Videos with Visual AnchorsSaelyne Yang, Jo Vermeulen, George Fitzmaurice2024arxiv 2403.05213
MM-PhyQA: Multimodal Physics Question-Answering With Multi-Image CoT PromptingAvinash Anand, Janak Kapuriya, Apoorv Singh2024arxiv 2404.08704
QA-TOOLBOX: Conversational Question-Answering for process task guidance in manufacturingRamesh Manuvinakurike, Elizabeth Watkins, Celal Savur2024arxiv 2412.02638
QuArch: A Question-Answering Dataset for AI Agents in Computer ArchitectureShvetank Prakash, Andrew Cheng, Jason Yik2025arxiv 2501.01892
DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace EditingXinyu Ma, Yifeng Xu, Yang Lin2025arxiv 2501.14371
Talking to GDELT Through Knowledge GraphsAudun Myers, Max Vargas, Sinan G. Aksoy2025arxiv 2503.07584