Jing Ye

Current evaluation paradigms for emotional support conversations tend to reward generic empathetic responses, yet they fail to assess whether the support is genuinely personalized to users’ unique psychological profiles and contextual needs. We introduce EmoHarbor , an automated evaluation framew...

Currently, most reinforcement learning tasks focus on domains like mathematics and programming, where verification is relatively straightforward. However, in subjective tasks such as role-playing, alignment techniques struggle to make progress, primarily because subjective reward modeling using t...