The Hypocrisy Gap: Quantifying Divergence Between Internal Belief and Chain-of-Thought Explanation via Sparse Autoencoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shiromani, Shikhar, Chaudhury, Archie, Kunda, Sri Pranav
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917243626979328
author Shiromani, Shikhar
Chaudhury, Archie
Kunda, Sri Pranav
author_facet Shiromani, Shikhar
Chaudhury, Archie
Kunda, Sri Pranav
contents Large Language Models (LLMs) frequently exhibit unfaithful behavior, producing a final answer that differs significantly from their internal chain of thought (CoT) reasoning in order to appease the user they are conversing with. In order to better detect this behavior, we introduce the Hypocrisy Gap, a mechanistic metric utilizing Sparse Autoencoders (SAEs) to quantify the divergence between a model's internal reasoning and its final generation. By mathematically comparing an internal truth belief, derived via sparse linear probes, to the final generated trajectory in latent space, we quantify and detect a model's tendency to engage in unfaithful behavior. Experiments on Gemma, Llama, and Qwen models using Anthropic's Sycophancy benchmark show that our method achieves an AUROC of 0.55-0.73 for detecting sycophantic runs and 0.55-0.74 for hypocritical cases where the model internally "knows" the user is wrong, consistently outperforming a decision-aligned log-probability baseline (0.41-0.50 AUROC).
format Preprint
id arxiv_https___arxiv_org_abs_2602_02496
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Hypocrisy Gap: Quantifying Divergence Between Internal Belief and Chain-of-Thought Explanation via Sparse Autoencoders
Shiromani, Shikhar
Chaudhury, Archie
Kunda, Sri Pranav
Computation and Language
Large Language Models (LLMs) frequently exhibit unfaithful behavior, producing a final answer that differs significantly from their internal chain of thought (CoT) reasoning in order to appease the user they are conversing with. In order to better detect this behavior, we introduce the Hypocrisy Gap, a mechanistic metric utilizing Sparse Autoencoders (SAEs) to quantify the divergence between a model's internal reasoning and its final generation. By mathematically comparing an internal truth belief, derived via sparse linear probes, to the final generated trajectory in latent space, we quantify and detect a model's tendency to engage in unfaithful behavior. Experiments on Gemma, Llama, and Qwen models using Anthropic's Sycophancy benchmark show that our method achieves an AUROC of 0.55-0.73 for detecting sycophantic runs and 0.55-0.74 for hypocritical cases where the model internally "knows" the user is wrong, consistently outperforming a decision-aligned log-probability baseline (0.41-0.50 AUROC).
title The Hypocrisy Gap: Quantifying Divergence Between Internal Belief and Chain-of-Thought Explanation via Sparse Autoencoders
topic Computation and Language
url https://arxiv.org/abs/2602.02496