Social Skill Training with Large Language Models

2024/04/05 by Diyi Yang, Caleb Ziems, Yang, Diyi +11 · 3 voices · 7 citations
Computer Science · Psychology · #Computer science #Geography #Psychology #Topic Modeling #Training (meteorology)

paper · pdf · doi:10.48550/arxiv.2404.04204

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2024/04/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

People rely on social skills like conflict resolution to communicate effectively and to thrive in both work and personal life. However, practice environments for social skills are typically out of reach for most people. How can we make social skill training more available, accessible, and inviting? Drawing upon interdisciplinary research from communication and psychology, this perspective paper identifies social skill barriers to enter specialized fields. Then we present a solution that leverages large language models for social skill training via a generic framework. Our AI Partner, AI Mentor framework merges experiential learning with realistic practice and tailored feedback. This work ultimately calls for cross-disciplinary innovation to address the broader implications for workforce development and social equality.

Cited by

• ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation
• When Large Language Models are Reliable for Judging Empathic Communication
• AI for Sustainable Future Foods
• LLM-Powered Virtual Patient Agents for Interactive Clinical Skills Training with Automated Feedback
• SNS-Bench-VL: Benchmarking Multimodal Large Language Models in Social Networking Services
• Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models

Discussions

• Social Skill Training with Large Language Models [hn, 104 points, 99 comments]
• Diyi’s paper: arxiv.org/abs/2404.04204 Diyi’s lab website: cs.stanford.edu/~diyiy/group... [bsky, 1 points, 0 comments]
• Social Skill Training with Large Language Models (arxiv.org) Main Link | Discussion [bsky, 0 points, 0 comments]

Related

• SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents
• An LLM-Guided Tutoring System for Social Skills Training
• SocialCoach: Personalized Social Skill Learning with RL-based Agentic Tutoring and Practice
• SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents
• Training Socially Aligned Language Models on Simulated Social Interactions