3 papers
cs.CL2026
GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking
Ziqi Zhu, Adithya Suresh, Tomal Deb +1
Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models (LLMs) struggle despite thei…
cs.CL2025
STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability
Guanghui Wang, Jinze Yu, Xing Zhang +5
Large Language Models (LLMs) are increasingly deployed for structured data generation, yet output consistency remains critical for production applications. We introduce a comprehen…
cs.CL2024
ADEQA: A Question Answer based approach for joint ADE-Suspect Extraction using Sequence-To-Sequence Transformers
Vinayak Arannil, Tomal Deb, Atanu Roy
Early identification of Adverse Drug Events (ADE) is critical for taking prompt actions while introducing new drugs into the market. These ADEs information are available through va…