averaging-bias

Tag

Cards List
#averaging-bias

Averaging Bias: Human Faithfulness Annotations are not Locally Faithful

arXiv cs.CL ↗ · 2026-08-04 Cached

This paper from Stony Brook University identifies 'Averaging Bias' in human faithfulness annotations for text summarization: global human labels correlate better with the average of per-sentence LLM judgments than with a strict conjunctive rule, meaning humans often label summaries as faithful even when they contain local factual errors.

0 favorites 0 likes
← Back to home

Submit Feedback