LLMs exhibit confirmation bias in chain-of-thought: strong internal beliefs, approximated by direct answer probabilities, skew both reasoning generation and how the final answer is chosen, which helps explain why CoT helps more on math than commonsense tasks.
Title resolution pending
1 Pith paper cite this work, alongside 7 external citations. Polarity classification is still indexing.
1
Pith paper citing it
7
external citations · OpenAlex
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unveiling Confirmation Bias in Chain-of-Thought Reasoning
LLMs exhibit confirmation bias in chain-of-thought: strong internal beliefs, approximated by direct answer probabilities, skew both reasoning generation and how the final answer is chosen, which helps explain why CoT helps more on math than commonsense tasks.