GPT-4o, Gemini-Pro, and Claude show less associative bias than human reasoners on collider graphs, making them more normatively aligned in likelihood judgments, but none fully demonstrates explaining away.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do Large Language Models Reason Causally Like Us? Even Better?
GPT-4o, Gemini-Pro, and Claude show less associative bias than human reasoners on collider graphs, making them more normatively aligned in likelihood judgments, but none fully demonstrates explaining away.