General-purpose LLMs reproduce some human-like merging behaviors such as intermittent control and spatial cue dependence but fail to consistently match responses to velocity cues and show divergent safety performance.
Explaining human interactions on the road by large-scale integration of computational psychological theory,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
General-purpose LLMs as Models of Human Driver Behavior: The Case of Simplified Merging
General-purpose LLMs reproduce some human-like merging behaviors such as intermittent control and spatial cue dependence but fail to consistently match responses to velocity cues and show divergent safety performance.