# Linear Probe Penalties Reduce LLM Sycophancy

arXiv: https://arxiv.org/abs/2412.00967 · HTML: https://mlsanity.com/paper/2412.00967/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 1 Dec 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)
- Mechanistic interpretability / [Steering and probing for LLM safety](https://mlsanity.com/mechinterp/steering-and-probing-for-llm-safety/)

## Builds on (most cited first, 13 of 13)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- [Simple synthetic data reduces sycophancy in large language models](https://mlsanity.com/paper/2308.03958/) (2023)
- [Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks](https://mlsanity.com/paper/2307.00175/) (2023)
- [Human language reveals a universal positivity bias](https://mlsanity.com/paper/1406.3855/) (2014)

## Built on by (most cited first, 28 of 28)

- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [Measuring Sycophancy of Language Models in Multi-turn Dialogues](https://mlsanity.com/paper/2505.23840/) (2025)
- [Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs](https://mlsanity.com/paper/2509.21305/) (2025)
- [BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs](https://mlsanity.com/paper/2510.04721/) (2025)
- [RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?](https://mlsanity.com/paper/2506.14261/) (2025)
- [Sycophancy Hides Linearly in the Attention Heads](https://mlsanity.com/paper/2601.16644/) (2026)
- [How RLHF Amplifies Sycophancy](https://mlsanity.com/paper/2602.01002/) (2026)
- [Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA](https://mlsanity.com/paper/2508.13743/) (2025)
- [Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT](https://mlsanity.com/paper/2510.00296/) (2025)
- [Consistency Training Helps Stop Sycophancy and Jailbreaks](https://mlsanity.com/paper/2510.27062/) (2025)
- [What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct](https://mlsanity.com/paper/2605.21778/) (2026)
- [The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes](https://mlsanity.com/paper/2602.15515/) (2026)
- [Preference Learning with Lie Detectors can Induce Honesty or Evasion](https://mlsanity.com/paper/2505.13787/) (2025)
- [Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models](https://mlsanity.com/paper/2509.16149/) (2025)
- [LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs](https://mlsanity.com/paper/2505.24451/) (2025)
- [PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models](https://mlsanity.com/paper/2512.19350/) (2025)
- [Automatically Finding Reward Model Biases](https://mlsanity.com/paper/2602.15222/) (2026)
- [Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition](https://mlsanity.com/paper/2604.05279/) (2026)
- [CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs](https://mlsanity.com/paper/2602.08939/) (2026)
- [Generative AI for Managerial Decision-Making under Ambiguity and Sycophancy](https://mlsanity.com/paper/2603.03970/) (2026)
- [Reasoning Models Know What's Important, and Encode It in Their Activations](https://mlsanity.com/paper/2604.18307/) (2026)
- [Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.01302/) (2026)
- [Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating](https://mlsanity.com/paper/2606.09068/) (2026)
- [Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs](https://mlsanity.com/paper/2606.16011/) (2026)
- [SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models](https://mlsanity.com/paper/2509.15174/) (2025)
- [Measuring and Detecting Harmful AI Sycophancy](https://mlsanity.com/paper/2608.05624/) (2026)
- [Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach](https://mlsanity.com/paper/2608.25267/) (2026)
- [Mitigating Social Sycophancy via Pluralistic Preference Optimization](https://mlsanity.com/paper/2610.02568/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are often sycophantic, prioritizing agreement with their users over accurate or objective statements. This problematic behavior becomes more pronounced during reinforcement learning from human feedback (RLHF), an LLM fine-tuning stage intended to align model outputs with human values. Instead of increasing accuracy and reliability, the reward model learned from RLHF often rewards sycophancy. We develop a linear probing method to identify and penalize markers of sycophancy within the reward model, producing rewards that discourage sycophantic behavior. Our experiments show that constructing and optimizing against this surrogate reward function reduces sycophantic behavior in multiple open-source LLMs. Our results suggest a generalizable methodology for reducing unwanted LLM behaviors that are not sufficiently disincentivized by RLHF fine-tuning.