# Ask don't tell: Reducing sycophancy in large language models

arXiv: https://arxiv.org/abs/2602.23971 · HTML: https://mlsanity.com/paper/2602.23971/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Measuring Sycophancy of Language Models in Multi-turn Dialogues](https://mlsanity.com/paper/2505.23840/) (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)
- [Be Friendly, Not Friends: How LLM Sycophancy Shapes User Trust](https://mlsanity.com/paper/2502.10844/) (2025)
- [HiBayES: A Hierarchical Bayesian Modeling Framework for AI Evaluation Statistics](https://mlsanity.com/paper/2505.05602/) (2025)
- [Challenging the Evaluator: LLM Sycophancy Under User Rebuttal](https://mlsanity.com/paper/2509.16533/) (2025)
- [Technological folie `a deux: Feedback Loops Between AI Chatbots and Mental Illness](https://mlsanity.com/paper/2507.19218/) (2025)
- [Skewed Score: A statistical framework to assess autograders](https://mlsanity.com/paper/2507.03772/) (2025)
- [People readily follow personal advice from AI but it does not improve their well-being](https://mlsanity.com/paper/2511.15352/) (2025)
- [Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence](https://mlsanity.com/paper/2510.01395/) (2025)

## Built on by (most cited first, 14 of 14)

- [Sycophantic AI makes human interaction feel more effortful and less satisfying over time](https://mlsanity.com/paper/2605.07912/) (2026)
- [MemSyco-Bench: Benchmarking Sycophancy in Agent Memory](https://mlsanity.com/paper/2607.01071/) (2026)
- [A Mechanistic View of Authority Hierarchy in LLM Sycophancy](https://mlsanity.com/paper/2607.00415/) (2026)
- [SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy](https://mlsanity.com/paper/2604.02423/) (2026)
- [Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy](https://mlsanity.com/paper/2605.12991/) (2026)
- [Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure](https://mlsanity.com/paper/2605.27996/) (2026)
- [Authority Bias in Language Models: Source Deference and User Agreement Are Not Interchangeable](https://mlsanity.com/paper/2609.37616/) (2026)
- [Escape from Delusional Echo Trap: Symmetry Breaking, Stochastic Dynamics and Mathematical Mitigation Strategies for Algorithmic Sycophancy](https://mlsanity.com/paper/2606.20718/) (2026)
- [SyPS: Measuring Sycophancy Prompt Sensitivity in Large Language Models](https://mlsanity.com/paper/2608.23837/) (2026)
- [Are You Sure You're Sure? Two Confounds in a Sycophancy Benchmark](https://mlsanity.com/paper/2609.32867/) (2026)
- [BenSyc: Benchmarking Conversational Sycophancy and Human Alignment in LLMs for Bengali Contexts](https://mlsanity.com/paper/2606.10061/) (2026)
- [Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy](https://mlsanity.com/paper/2607.24304/) (2026)
- [Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach](https://mlsanity.com/paper/2608.25267/) (2026)
- [XYEval: Agents say yes to bad advice](https://mlsanity.com/paper/2609.23939/) (2026)

## Abstract (arXiv)

Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an alignment failure, particularly in high-stakes advisory and social contexts. While prior work has documented conversational features correlated with sycophancy, we lack a systematic understanding of what provokes or prevents AI sycophancy. Here, we present a set of controlled experimental studies where we first isolate how input framing influences sycophancy, and second, leverage these findings to develop mitigation strategies. In a nested factorial design, we compare questions to various non-questions where we vary three orthogonal factors: epistemic certainty (statement, belief, conviction), perspective (I- vs user-perspective), and affirmation vs negation. Measuring expressed sycophancy, how sycophantically a model phrases its free-text response, we show that (1) sycophancy is substantially higher in response to non-questions compared to questions. Additionally, we find that (2) sycophancy increases monotonically with epistemic certainty conveyed by the user, and (3) is amplified by I-perspective framing. Building on this, we show that asking a model to convert non-questions into questions before answering significantly reduces sycophancy. Importantly, this effect is stronger than a simple baseline prompt asking models "not to be sycophantic". In a follow-up experiment, we show that these framing effects generalise to choice sycophancy, which answer a model commits to, in a more context-rich, personalised setting: when a model is given extensive knowledge of a user and must select between forced binary choices, the same question vs. statement framing shapes how often it picks the answer aligned with the user's stance. Our work offers a practical and effective input-level mitigation that both developers and users can easily adopt.