pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CY 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Implicit Bias-Like Patterns in Reasoning Models

cs.CY · 2025-03-14 · unverdicted · novelty 6.0

Reasoning models expend more tokens on association-incompatible tasks than compatible ones, indicating greater effort on counter-stereotypical information, except for Claude 3.7 Sonnet which shows the reverse pattern linked to its bias-focused reasoning.

citing papers explorer

Showing 1 of 1 citing paper.

  • Implicit Bias-Like Patterns in Reasoning Models cs.CY · 2025-03-14 · unverdicted · none · ref 29

    Reasoning models expend more tokens on association-incompatible tasks than compatible ones, indicating greater effort on counter-stereotypical information, except for Claude 3.7 Sonnet which shows the reverse pattern linked to its bias-focused reasoning.