# Token-Level Diagnosis of Sycophancy in LLMs with Attribution-Guided Steering

arXiv: https://arxiv.org/abs/2607.28906 · HTML: https://mlsanity.com/paper/2607.28906/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Probing deception, bias and beliefs, one of 13 directions in Mechanistic interpretability.
- Builds on 22 of its 51 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Placed in

- Mechanistic interpretability / [Probing deception, bias and beliefs](https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/)

## Builds on (most cited first, 22 of 22)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [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)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Captum: A unified and generic model interpretability library for PyTorch](https://mlsanity.com/paper/2009.07896/) (2020)
- [Measuring Sycophancy of Language Models in Multi-turn Dialogues](https://mlsanity.com/paper/2505.23840/) (2025)
- [Sycophancy in Large Language Models: Causes and Mitigations](https://mlsanity.com/paper/2411.15287/) (2024)
- [TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models](https://mlsanity.com/paper/2503.11656/) (2025)
- [Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias](https://mlsanity.com/paper/2401.01989/) (2024)
- [Sycophancy Hides Linearly in the Attention Heads](https://mlsanity.com/paper/2601.16644/) (2026)
- [Accounting for Sycophancy in Language Model Uncertainty Estimation](https://mlsanity.com/paper/2410.14746/) (2024)
- [Positional Biases Shift as Inputs Approach Context Window Limits](https://mlsanity.com/paper/2508.07479/) (2025)
- [PARROT: Persuasion and Agreement Robustness Rating of Output Truth -- A Sycophancy Robustness Benchmark for LLMs](https://mlsanity.com/paper/2511.17220/) (2025)
- [GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs](https://mlsanity.com/paper/2507.18043/) (2025)

## Built on by (most cited first, 1 of 1)

- [How Do Language Models Choose Between Context and Memory?](https://mlsanity.com/paper/2609.00753/) (2026)

## Abstract (arXiv)

Sycophancy refers to the tendency for large language models (LLMs) to match user beliefs at the cost of factual correctness, thereby undermining model reliability. Prior work on evaluating sycophancy in LLMs aims to assess whether a model's output matches an authority's claim, but cannot reveal which part of the prompt drives this sycophantic behavior. To bridge this gap, we investigate the relationship of sycophantic responses with an authority's credentials, their assertive claim, and the problem statement. We introduce the Authority Share Index (ASI), an Integrated Gradients-based token attribution method, which measures the degree to which a model's decision is driven by authority-related text. Through extensive experiments across five models and 30 test configurations, we find that sycophantic responses consistently direct more attention toward authority tokens than resistant ones. Moreover, our token attribution method reveals that for the sycophantic cases, the claim asserted by the authority receives more attention than the authority's credentials. Building on these findings, we propose attribution-guided contrastive activation steering to mitigate LLM sycophancy. Our method constructs a steering vector from high-attribution tokens of sycophantic and resistant responses, selectively pushing models toward resistance. This enables inference-time steering without retraining, lowering sycophancy from 96% to 25% in the strongest case. Together, our results show that token-level attribution can both explain what drives sycophancy and directly inform a practical intervention.