AI RESEARCH
BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents
arXiv CS.CL
•
ArXi:2603.23848v1 Announce Type: new LLMs are increasingly used as long-running conversational agents, yet every major benchmark evaluating their memory treats user information as static facts to be d and retrieved. That's the wrong model. People change their minds, and over extended interactions, phenomena like opinion drift, over-alignment, and confirmation bias start to matter a lot. We evaluate seven models including GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro, LLaMA-3, and Mistral-Large under zero-shot and retrieval-augmented generation (RAG) settings.