# LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit

arXiv: https://arxiv.org/abs/2604.19117 · HTML: https://mlsanity.com/paper/2604.19117/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 28 of 28)

- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Attribution Patching Outperforms Automated Circuit Discovery](https://mlsanity.com/paper/2310.10348/) (2023)
- [The Hydra Effect: Emergent Self-repair in Language Model Computations](https://mlsanity.com/paper/2307.15771/) (2023)
- [Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms](https://mlsanity.com/paper/2403.17806/) (2024)
- [Circuit Component Reuse Across Tasks in Transformer Language Models](https://mlsanity.com/paper/2310.08744/) (2023)
- [How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions](https://mlsanity.com/paper/2309.15840/) (2023)
- [Overthinking the Truth: Understanding how Language Models Process False Demonstrations](https://mlsanity.com/paper/2307.09476/) (2023)
- [Truth is Universal: Robust Detection of Lies in LLMs](https://mlsanity.com/paper/2407.12831/) (2024)
- [Convergent Linear Representations of Emergent Misalignment](https://mlsanity.com/paper/2506.11618/) (2025)
- [From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning](https://mlsanity.com/paper/2409.01658/) (2024)
- [When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models](https://mlsanity.com/paper/2508.02087/) (2025)
- [Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs](https://mlsanity.com/paper/2509.21305/) (2025)
- [Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patching](https://mlsanity.com/paper/2311.15131/) (2023)
- [Sycophancy Hides Linearly in the Attention Heads](https://mlsanity.com/paper/2601.16644/) (2026)
- [The Truthfulness Spectrum Hypothesis](https://mlsanity.com/paper/2602.20273/) (2026)
- [Can LLMs Lie? Investigation beyond Hallucination](https://mlsanity.com/paper/2509.03518/) (2025)

## Built on by (most cited first, 10 of 10)

- [The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads](https://mlsanity.com/paper/2608.04570/) (2026)
- [From Trait Vectors to Circuits: Tracing Refusal and Sycophancy Through Language Models](https://mlsanity.com/paper/2609.22224/) (2026)
- [Resist, Update, Reject: Preference Optimization Installs a Prior-Dependent Reliability Switch](https://mlsanity.com/paper/2609.22359/) (2026)
- ["You're Right, Let Me Fix It": How LLM Agents Damage Correct Work When Falsely Accused](https://mlsanity.com/paper/2609.32616/) (2026)
- [Measuring Collapse and Correction in Homogeneous-Panel LLM Debate](https://mlsanity.com/paper/2609.35279/) (2026)
- [Tracing mechanisms of sycophantic agreement in language models](https://mlsanity.com/paper/2609.35822/) (2026)
- [Multi-agent discussion gains less when dissent is withheld](https://mlsanity.com/paper/2609.38324/) (2026)
- [Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise](https://mlsanity.com/paper/2610.02702/) (2026)
- [Pushback in a Haystack: Language Models Respond to Factual Errors Ambiguously and Ineffectively](https://mlsanity.com/paper/2610.17703/) (2026)
- [Seeing Through the Forgery Is Not Enough: Regressive Sycophancy under Fabricated Evidence in Medical Vision-Language Models](https://mlsanity.com/paper/2610.17989/) (2026)

## Abstract (arXiv)

When a language model agrees with a user's false belief, is it failing to detect the error, or noticing and agreeing anyway? We show the latter. Across twelve open-weight models from five labs, spanning small to frontier scale, the same small set of attention heads carries a "this statement is wrong" signal, whether the model is evaluating a claim on its own or being pressured to agree with a user. Silencing these heads flips sycophantic behavior sharply while leaving factual accuracy intact, so the circuit controls deference rather than knowledge. Edge-level path patching confirms that the same head-to-head connections drive sycophancy, factual lying, and instructed lying. Opinion-agreement, where no factual ground truth exists, reuses these head positions but writes into an orthogonal direction, ruling out a simple "truth-direction" reading of the substrate. Alignment training leaves this circuit in place: an RLHF refresh cuts sycophantic behavior roughly tenfold while the shared heads persist or grow, a pattern that replicates on an independent model family and under targeted anti-sycophancy DPO. When these models sycophant, they register that the user is wrong and agree anyway.