ICML Paper Reveals LLM Salience Bias: Hijacked by Distractors in Commonsense

Zheng Wu · hf · 2026-08-03

Research reveals that Large Language Models exhibit a critical Salience Bias during commonsense reasoning: models are easily hijacked by useless explicit distractors (e.g., numerical values), leading them to ignore implicit physical or commonsense prerequisites.

Key Findings:

The findings relocate the bottleneck of commonsense reasoning failures from model competence to elicitation, and the code is open-sourced.

Related event: ICML Paper Reveals Salience Bias in LLMs(2 posts)→

Original post →

More from Models

Models channel →