Empirical study of 21k conversations finds human-like behaviors pervasive in LLMs but varying by model and user factors, with differing human judgments on appropriateness and partial controllability via prompts.
LLM Behavior Categories, Definitions, and Examples
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts
Empirical study of 21k conversations finds human-like behaviors pervasive in LLMs but varying by model and user factors, with differing human judgments on appropriateness and partial controllability via prompts.