all AI news
Conformity, Confabulation, and Impersonation: Persona Inconstancy in Multi-Agent LLM Collaboration
May 8, 2024, 4:47 a.m. | Razan Baltaji, Babak Hemmatian, Lav R. Varshney
cs.CL updates on arXiv.org arxiv.org
Abstract: This study explores the sources of instability in maintaining cultural personas and opinions within multi-agent LLM systems. Drawing on simulations of inter-cultural collaboration and debate, we analyze agents' pre- and post-discussion private responses alongside chat transcripts to assess the stability of cultural personas and the impact of opinion diversity on group outcomes. Our findings suggest that multi-agent discussions can encourage collective decisions that reflect diverse perspectives, yet this benefit is tempered by the agents' susceptibility …
abstract agent agents analyze arxiv chat collaboration confabulation conformity cs.ai cs.cl impersonation llm multi-agent opinions personas responses simulations stability study systems transcripts type
More from arxiv.org / cs.CL updates on arXiv.org
ALBA: Adaptive Language-based Assessments for Mental Health
2 days, 12 hours ago |
arxiv.org
PACE: Improving Prompt with Actor-Critic Editing for Large Language Model
2 days, 12 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US