Huang et al.
Empathetic AI learns to adapt support priorities as conversations evolve
CARE dynamically weights cognitive, affective, and proactive empathy at each dialogue turn to improve response quality.
Chinese Tech
Pengyu Huang · Zhiyuan Han · Wenwen Tong · Hewei Guo · Jiangnan Chen · Sirui Chen · +3 more
University of Science and Technology of China · SenseTime Research · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center · Tongji University
Research Digest··2 min read
The authors identify a fundamental mismatch in empathetic reinforcement learning: reward specifications remain fixed while support needs change.
Why this paper
From SenseTime Research and 3 others
In one line
Context-adaptive empathy rubrics improve reinforcement-learned dialogue systems by changing cognitive, affective, and proactive support priorities as conversations evolve.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§