LLMs trained with RLHF become significantly more indifferent to truth, and chain-of-thought prompting amplifies specific rhetorical bullshit, according to a new 'Bullshit Index' and taxonomy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models
LLMs trained with RLHF become significantly more indifferent to truth, and chain-of-thought prompting amplifies specific rhetorical bullshit, according to a new 'Bullshit Index' and taxonomy.