# When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models

arXiv: https://arxiv.org/abs/2508.02087 · HTML: https://mlsanity.com/paper/2508.02087/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 55 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Builds on (most cited first, 30 of 32)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [In-Context Learning Creates Task Vectors](https://mlsanity.com/paper/2310.15916/) (2023)
- [OLMoE: Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2409.02060/) (2024)
- [Sycophancy in Large Language Models: Causes and Mitigations](https://mlsanity.com/paper/2411.15287/) (2024)
- [From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning](https://mlsanity.com/paper/2409.01658/) (2024)
- [Understanding Aha Moments: from External Observations to Internal Mechanisms](https://mlsanity.com/paper/2504.02956/) (2025)
- [Characterizing Mechanisms for Factual Recall in Language Models](https://mlsanity.com/paper/2310.15910/) (2023)
- [Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing](https://mlsanity.com/paper/2410.06331/) (2024)
- [Understanding the Repeat Curse in Large Language Models from a Feature Perspective](https://mlsanity.com/paper/2504.14218/) (2025)
- [Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback](https://mlsanity.com/paper/2505.20075/) (2025)
- [EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification](https://mlsanity.com/paper/2502.06852/) (2025)
- [Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs](https://mlsanity.com/paper/2506.07180/) (2025)
- [Accounting for Sycophancy in Language Model Uncertainty Estimation](https://mlsanity.com/paper/2410.14746/) (2024)
- [A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2406.12255/) (2024)
- [Towards User-level Private Reinforcement Learning with Human Feedback](https://mlsanity.com/paper/2502.17515/) (2025)
- [Understanding How Value Neurons Shape the Generation of Specified Values in LLMs](https://mlsanity.com/paper/2505.17712/) (2025)

## Built on by (most cited first, 30 of 50)

- [Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs](https://mlsanity.com/paper/2509.21305/) (2025)
- [When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning](https://mlsanity.com/paper/2510.07517/) (2025)
- [Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians](https://mlsanity.com/paper/2602.19141/) (2026)
- [Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models](https://mlsanity.com/paper/2508.10599/) (2025)
- [Ask don't tell: Reducing sycophancy in large language models](https://mlsanity.com/paper/2602.23971/) (2026)
- [A Rational Analysis of the Effects of Sycophantic AI](https://mlsanity.com/paper/2602.14270/) (2026)
- [MemSyco-Bench: Benchmarking Sycophancy in Agent Memory](https://mlsanity.com/paper/2607.01071/) (2026)
- [LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit](https://mlsanity.com/paper/2604.19117/) (2026)
- [A Mechanistic View of Authority Hierarchy in LLM Sycophancy](https://mlsanity.com/paper/2607.00415/) (2026)
- [Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy](https://mlsanity.com/paper/2603.16643/) (2026)
- [Dissociating the Internal Representations of Sycophancy in LLMs](https://mlsanity.com/paper/2607.07003/) (2026)
- [Benchmarking and Mitigating Sycophancy in Medical Vision Language Models](https://mlsanity.com/paper/2509.21979/) (2025)
- [Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs](https://mlsanity.com/paper/2603.00024/) (2026)
- [Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models](https://mlsanity.com/paper/2606.10949/) (2026)
- [Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images](https://mlsanity.com/paper/2603.08486/) (2026)
- [The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications](https://mlsanity.com/paper/2604.24668/) (2026)
- [Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy](https://mlsanity.com/paper/2605.12991/) (2026)
- [Affective Context Amplifies Sycophancy in LLM Responses](https://mlsanity.com/paper/2608.21242/) (2026)
- [When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making](https://mlsanity.com/paper/2602.04003/) (2026)
- [Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness](https://mlsanity.com/paper/2603.10771/) (2026)
- [Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models](https://mlsanity.com/paper/2604.11609/) (2026)
- [Authority Bias in Language Models: Source Deference and User Agreement Are Not Interchangeable](https://mlsanity.com/paper/2609.37616/) (2026)
- [Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions](https://mlsanity.com/paper/2511.07669/) (2025)
- [Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models](https://mlsanity.com/paper/2602.00300/) (2026)
- [Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution](https://mlsanity.com/paper/2602.04918/) (2026)
- [Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation](https://mlsanity.com/paper/2606.05403/) (2026)
- [Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs](https://mlsanity.com/paper/2606.16011/) (2026)
- [Escape from Delusional Echo Trap: Symmetry Breaking, Stochastic Dynamics and Mathematical Mitigation Strategies for Algorithmic Sycophancy](https://mlsanity.com/paper/2606.20718/) (2026)
- [Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs](https://mlsanity.com/paper/2607.12985/) (2026)
- [One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs](https://mlsanity.com/paper/2609.18998/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often exhibit sycophantic behavior, agreeing with user-stated opinions even when those contradict factual knowledge. While prior work has documented this tendency, the internal mechanisms that enable such behavior remain poorly understood. In this paper, we provide a mechanistic account of how sycophancy arises within LLMs. We first systematically study how user opinions induce sycophancy across different model families. We find that simple opinion statements reliably induce sycophancy, whereas user expertise framing has a negligible impact. Through logit-lens analysis and causal activation patching, we identify a two-stage emergence of sycophancy: (1) a late-layer output preference shift and (2) deeper representational divergence. We also verify that user authority fails to influence behavior because models do not encode it internally. In addition, we examine how grammatical perspective affects sycophantic behavior, finding that first-person prompts (``I believe...'') consistently induce higher sycophancy rates than third-person framings (``They believe...'') by creating stronger representational perturbations in deeper layers. These findings highlight that sycophancy is not a surface-level artifact but emerges from a structural override of learned knowledge in deeper layers, with implications for alignment and truthful AI systems.