2025
Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL
EMNLP 2025
The paper shows that parameter-efficient reinforcement learning (PE-RL) is a highly effective training regime to improve large language models’ (LLMs) ability to answer queries on sensitive topics with a Neutral Point of View (NPOV), i.e. to provide significantly more informative, diverse and impart