LLMs exhibit large systematic disparities in quote attribution accuracy across race, gender, and intersectional groups, along with widespread and uneven suppression of attributions.
Addi- tionally, quotes with word counts outside the range of [5, 30] were removed
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Attribution Bias in Large Language Models
LLMs exhibit large systematic disparities in quote attribution accuracy across race, gender, and intersectional groups, along with widespread and uneven suppression of attributions.