2 papers
cs.CL2026
Synthesis and Evaluation of Long-term History-aware Medical Dialogue
Hebin Hu, Renke Dai, Ah-Hwee Tan +1
An effective healthcare agent must be able to recall and reason over a patient's longitudinal medical history. However, the absence of datasets with realistic long-term dialogue ti…
cs.LG2023
Deep Reinforcement Learning with Explicit Context Representation
Francisco Munguia-Galeano, Ah-Hwee Tan, Ze Ji
Reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems. However, most RL algorithms lack an explicit method that would allow lea…