Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approachby Zhouyu Jiang, Mengshu Sun,…
BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalby Hongjin Su, Howard Yen, Mengzhou Xia,…
Black-box Model Ensembling for Textual and Visual Question Answering via Information Fusionby Yuxi Xia, Kilm…
Multimodal Reranking for Knowledge-Intensive Visual Question Answeringby Haoyang Wen, Honglei Zhuang, Hamed Zamani, Alexander Hauptmann,…
MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipelineby Donghoon Han, Eunhwan…
Follow-Up Questions Improve Documents Generated by Large Language Modelsby Bernadette J TixFirst submitted to arxiv…
Better RAG using Relevant Information Gainby Marc Pickett, Jeremy Hartman, Ayan Kumar Bhowmick, Raquib-ul Alam,…
Geode: A Zero-shot Geospatial Question-Answering Agent with Explicit Reasoning and Precise Spatio-Temporal Retrievalby Devashish Vikas…
TM-PATHVQA:90000+ Textless Multilingual Questions for Medical Visual Question Answeringby Tonmoy Rajkhowa, Amartya Roy Chowdhury, Sankalp…
Graphusion: Leveraging Large Language Models for Scientific Knowledge Graph Fusion and Construction in NLP Educationby…