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

• URL: http://arxiv.org/abs/2607.28906v1
• Date: Fri, 31 Jul 2026 00:05:36 GMT
• Title: Token-Level Diagnosis of Sycophancy in LLMs with Attribution-Guided Steering
• Abstract summary: Sycophancy refers to the tendency for large language models to match user beliefs at the cost of factual correctness.<n>We introduce the Authority Share Index (ASI), which measures the degree to which a model's decision is driven by authority-related text.<n>We find that sycophantic responses consistently direct more attention toward authority tokens than resistant ones.
• Score: 19.708436827458744
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts [0.300988853836121]
  Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure.<n>We introduce a shared contrastive signal, built from matched prompts with and without a stated belief, that identifies where sycophancy lives.<n>Our results demonstrate that sycophancy resides in identifiable computational subcircuits and can be selectively steered.
  arXiv  Detail & Related papers  (2026-08-16T11:30:26Z)
• Mitigating LLM Sycophancy in Code Smell Detection Using Evidence-Guided Reasoning Prompts [0.0]
  We present the first systematic empirical study of sycophancy bias in large language models.<n>We show that sycophancy bias poses a critical threat to the reliability of LLM-based code smell detection.<n>We propose Evidence-Guided Debiasing Prompting (EGDP), a structured prompting strategy that enforces evidence-first reasoning.
  arXiv  Detail & Related papers  (2026-07-11T17:35:25Z)
• A Mechanistic View of Authority Hierarchy in LLM Sycophancy [0.09085204695117637]
  We show that authority-induced sycophancy is not a surface-level output bias but mechanistic knowledge erasure.<n>Our findings suggest that authority-induced sycophancy is not a surface-level output bias but mechanistic knowledge erasure.
  arXiv  Detail & Related papers  (2026-07-01T04:16:59Z)
• Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models [46.26628756478016]
  Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data.<n>We show that reasoning conflicts are internally detectable, as confidence scores significantly drop during conflicting episodes.<n>Our findings establish that while LLM reasoning is anchored to concrete instances, active mechanistic interventions can effectively decouple logical schemata from data.
  arXiv  Detail & Related papers  (2026-04-29T22:55:40Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Decoding the Critique Mechanism in Large Reasoning Models [50.821607345799386]
  Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions.<n>We investigate how current LRMs recover from errors by inserting arithmetic mistakes in their intermediate reasoning steps.<n>We find that despite the error propagating through the chain-of-thought, the model still reaches the correct final answer.
  arXiv  Detail & Related papers  (2026-03-17T10:03:30Z)
• Mechanistic Indicators of Steering Effectiveness in Large Language Models [3.635648354808971]
  Activation-based steering enables Large Language Models to exhibit targeted behaviors by intervening on intermediate activations without retraining.<n>Despite its widespread use, the mechanistic factors that govern when steering succeeds or fails remain poorly understood.<n>We investigate whether the reliability of steering can be diagnosed using internal model signals.
  arXiv  Detail & Related papers  (2026-02-02T06:56:22Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking [58.475471437150674]
  We propose sequential watermarking for soft prompts (SWAP)<n>SWAP encodes watermarks through a specific order of defender-specified out-of-distribution classes.<n>Experiments on 11 datasets demonstrate SWAP's effectiveness, harmlessness, and robustness against potential adaptive attacks.
  arXiv  Detail & Related papers  (2025-11-05T13:48:48Z)
• On Reasoning Strength Planning in Large Reasoning Models [50.61816666920207]
  We find evidence that LRMs pre-plan the reasoning strengths in their activations even before generation.<n>We then uncover that LRMs encode this reasoning strength through a pre-allocated directional vector embedded in the activations of the model.<n>Our work provides new insights into the internal mechanisms of reasoning in LRMs and offers practical tools for controlling their reasoning behaviors.
  arXiv  Detail & Related papers  (2025-06-10T02:55:13Z)
• Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability [53.51560766150442]
  Critical tokens are elements within reasoning trajectories that significantly influence incorrect outcomes.<n>We present a novel framework for identifying these tokens through rollout sampling.<n>We show that identifying and replacing critical tokens significantly improves model accuracy.
  arXiv  Detail & Related papers  (2024-11-29T18:58:22Z)
• Sycophancy in Vision-Language Models: A Systematic Analysis and an Inference-Time Mitigation Framework [18.54098084470481]
  We analyze sycophancy across vision-language benchmarks and propose an inference-time mitigation framework.<n>Our framework effectively mitigates sycophancy across all evaluated models, while maintaining performance on neutral prompts.
  arXiv  Detail & Related papers  (2024-08-21T01:03:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.