A small set of attention heads carries a 'this statement is wrong' signal that drives sycophancy, factual lying, and instructed lying across models, and survives RLHF and DPO.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
citing papers explorer
-
LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit
A small set of attention heads carries a 'this statement is wrong' signal that drives sycophancy, factual lying, and instructed lying across models, and survives RLHF and DPO.
- PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization