# When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models

arXiv: https://arxiv.org/abs/2605.05403 · HTML: https://mlsanity.com/paper/2605.05403/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 49 references that are in the map.
- First posted on arXiv 6 May 2026.

## Builds on (most cited first, 30 of 39)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [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)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing](https://mlsanity.com/paper/2001.00973/) (2020)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [SycEval: Evaluating LLM Sycophancy](https://mlsanity.com/paper/2502.08177/) (2025)
- [Measuring Sycophancy of Language Models in Multi-turn Dialogues](https://mlsanity.com/paper/2505.23840/) (2025)
- [From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots](https://mlsanity.com/paper/1801.01957/) (2018)
- [When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour](https://mlsanity.com/paper/2311.09410/) (2023)
- [When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models](https://mlsanity.com/paper/2508.02087/) (2025)
- [Large Language Models Produce Responses Perceived to be Empathic](https://mlsanity.com/paper/2403.18148/) (2024)
- [TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models](https://mlsanity.com/paper/2503.11656/) (2025)
- [Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians](https://mlsanity.com/paper/2602.19141/) (2026)
- [LLM-based Cognitive Models of Students with Misconceptions](https://mlsanity.com/paper/2410.12294/) (2024)
- [A Rational Analysis of the Effects of Sycophantic AI](https://mlsanity.com/paper/2602.14270/) (2026)
- [Reasoning Isn't Enough: Examining Truth-Bias and Sycophancy in LLMs](https://mlsanity.com/paper/2506.21561/) (2025)
- [From Sycophancy to Deception: A Unified Taxonomy for LLM Spontaneous Misalignment](https://mlsanity.com/paper/2604.04788/) (2026)
- [The Term 'Agent' Has Been Diluted Beyond Utility and Requires Redefinition](https://mlsanity.com/paper/2508.05338/) (2025)

## Abstract (arXiv)

This position paper argues that sycophancy in LLMs is a boundary failure between social alignment and epistemic integrity. Existing work often operationalizes sycophancy through external behavior such as agreement with incorrect user beliefs, position reversals, or deviation from an objective standard of correctness. These formulations capture only overt forms of the phenomenon and leave subtler boundary failures involving epistemic integrity and social alignment underspecified. We argue that sycophancy should not be understood as agreement alone, but as alignment behavior that displaces independent epistemic judgment. To clarify this boundary, we propose a three-condition framework for sycophancy. First, the user expresses a cue in the form of a belief, preference, or self-concept. Second, the model shifts toward that cue through alignment behavior. Third, this shift compromises epistemic accuracy, independent reasoning, or appropriate correction. We also introduce a taxonomy for classifying sycophancy, consisting of alignment targets, mechanisms, and severity. The paper concludes by discussing implications for alignment evaluation and argues for boundary-aware assessment, structured rubrics, and mitigation strategies, while situating these proposals alongside alternative views of sycophancy.