Talent or Luck? Evaluating Attribution Bias in Large Language Models

Chahat Raj, Mahika Banerjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu
5/28/2025
cs.CL

No official code found. Best implementation: chahatraj/TalentorLuck (1 star, last commit 2025-05-23).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

chahatraj/TalentorLuckCommunity100%
10PythonMay 19, 20251 years ago

Similar Papers

Anchors in the Machine: Behavioral and Attributional Evidence of Anchoring Bias in LLMs

83% match1 repo2025

A Japanese Benchmark for Evaluating Social Bias in Reasoning Based on Attribution Theory

83% match2026

Inference-Time Reasoning Selectively Reduces Implicit Social Bias in Large Language Models

83% match2026

The Bias is in the Details: An Assessment of Cognitive Bias in LLMs

83% match2025

Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models

83% match2025

Ask LLMs Directly, "What shapes your bias?": Measuring Social Bias in Large Language Models

82% match1 repo12024

Cite this paper

@article{raj2025talent,
  title  = {Talent or Luck? Evaluating Attribution Bias in Large Language Models},
  author = {Chahat Raj and Mahika Banerjee and Aylin Caliskan and Antonios Anastasopoulos and Ziwei Zhu},
  year   = {2025},
  eprint = {2505.22910},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.22910v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.22910.svg)](https://codeofpaper.com/paper/2505.22910)

Discussion