2 papers
cs.CL2025
Recon, Answer, Verify: Agents in Search of Truth
Satyam Shukla, Himanshu Dutta, Pushpak Bhattacharyya
Automated fact checking with large language models (LLMs) offers a scalable alternative to manual verification. Evaluating fact checking is challenging as existing benchmark datase…
cs.CL2025
GRAFT: A Graph-based Flow-aware Agentic Framework for Document-level Machine Translation
Himanshu Dutta, Sunny Manchanda, Prakhar Bapat +2
Document level Machine Translation (DocMT) approaches often struggle with effectively capturing discourse level phenomena. Existing approaches rely on heuristic rules to segment do…