Reposted by Swabha
Reasoning about the "why" behind user behavior can improve LLM personas! ✨🧠📈
📝Excited to share our new work: Improving LLM Personas via Rationalization with Psychological Scaffolds
🔗 arxiv.org/abs/2504.17993
🧵 (1/n)
Swabha
@swabhs.bsky.social
2.7K followers 200 following 5 posts
Assistant Professor of CS, University of Southern California. NLP / ML.
