no code implementations • 7 Apr 2024 • Sanwoo Lee, Yida Cai, Desong Meng, Ziyang Wang, Yunfang Wu
Then, an LLM is prompted to extract trait scores from several conversational rounds, each round scoring one of the traits based on the scoring criteria.
1 code implementation • 3 Apr 2024 • Ziyang Wang, Sanwoo Lee, Hsiu-Yuan Huang, Yunfang Wu
Our proposed method establishes a new architecture for prompt tuning that sheds light on how linguistic features can be easily adapted to linguistic-related tasks.