Talent or Luck? Evaluating Attribution Bias in Large Language Models
This work addresses fairness issues in LLMs for users affected by biased decision-making, but it is incremental as it builds on existing social bias research.
The paper tackled the problem of attribution bias in large language models (LLMs) by proposing a cognitively grounded evaluation framework to identify how reasoning disparities lead to biases based on demographics, with results highlighting fairness implications.
When a student fails an exam, do we tend to blame their effort or the test's difficulty? Attribution, defined as how reasons are assigned to event outcomes, shapes perceptions, reinforces stereotypes, and influences decisions. Attribution Theory in social psychology explains how humans assign responsibility for events using implicit cognition, attributing causes to internal (e.g., effort, ability) or external (e.g., task difficulty, luck) factors. LLMs' attribution of event outcomes based on demographics carries important fairness implications. Most works exploring social biases in LLMs focus on surface-level associations or isolated stereotypes. This work proposes a cognitively grounded bias evaluation framework to identify how models' reasoning disparities channelize biases toward demographic groups.