Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models

• URL: http://arxiv.org/abs/2601.21183v1
• Date: Thu, 29 Jan 2026 02:34:16 GMT
• Title: Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models
• Abstract summary: Reasoning models frequently agree with incorrect user suggestions.<n>We introduce emphsycophantic anchors -- sentences that causally lock models into user agreement.<n>We show that anchors can be reliably detected and quantified mid-inference.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning models frequently agree with incorrect user suggestions -- a behavior known as sycophancy. However, it is unclear where in the reasoning trace this agreement originates and how strong the commitment is. To localize and quantify this behavior, we introduce \emph{sycophantic anchors} -- sentences that causally lock models into user agreement. Analyzing over 10,000 counterfactual rollouts on a distilled reasoning model, we show that anchors can be reliably detected and quantified mid-inference. Linear probes distinguish sycophantic anchors with 84.6\% balanced accuracy, while activation-based regressors predict the magnitude of the commitment ($R^2 = 0.74$). We further observe asymmetry where sycophantic anchors are significantly more distinguishable than correct reasoning anchors, and find that sycophancy builds gradually during reasoning, revealing a potential window for intervention. These results offer sentence-level mechanisms for localizing model misalignment mid-inference.

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)
• Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models [55.788110316999166]
  We compare reasoning models produced via supervised fine-tuning, RL-based post-training, and distillation against instruction-tuned baselines.<n>We observe that reasoning models often improve on reasoning benchmarks but exhibit alignment regressions.<n>These regressions are consistent with behavioral drift from the instruction-tuned baseline, measured by KL divergence.
  arXiv  Detail & Related papers  (2026-06-09T16:14:27Z)
• SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy [1.4732811715354452]
  SWAY is an unsupervised computational linguistic measure of sycophancy.<n>We develop a counterfactual prompting mechanism to identify how much a model's agreement shifts under positive or negative linguistic pressure.<n>We introduce a counterfactual mitigation strategy teaching models to consider what the answer would be if opposite assumptions were suggested.
  arXiv  Detail & Related papers  (2026-04-02T18:00:14Z)
• 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)
• The Hypocrisy Gap: Quantifying Divergence Between Internal Belief and Chain-of-Thought Explanation via Sparse Autoencoders [0.0]
  We introduce the Hypocrisy Gap to quantify the divergence between a model's internal reasoning and its final generation.<n>By mathematically comparing an internal truth belief, derived via sparse linear probes, to the final generated trajectory in latent space, we quantify and detect a model's tendency to engage in unfaithful behavior.
  arXiv  Detail & Related papers  (2026-01-14T00:40:40Z)
• Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents [0.0]
  We introduce textbfProject Ariadne, a novel XAI framework to audit the causal integrity of agentic reasoning.<n>Unlike existing interpretability methods that rely on surface-level textual similarity, Project Ariadne performs textbfhard interventions ($do$-calculus) on intermediate reasoning nodes.<n>Our empirical evaluation of state-of-the-art models reveals a persistent textitFaithfulness Gap.
  arXiv  Detail & Related papers  (2026-01-05T18:05:29Z)
• How Does Prefix Matter in Reasoning Model Tuning? [57.69882799751655]
  We fine-tune three R1 series models across three core model capabilities: reasoning (mathematics), coding, safety, and factuality.<n>Results show that prefix-conditioned SFT improves both safety and reasoning performance, yielding up to +6% higher Safe@1 accuracy.
  arXiv  Detail & Related papers  (2026-01-04T18:04:23Z)
• Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models [0.0]
  Large language models internalize a structural trade-off between truthfulness and obsequious flattery.<n>This latent bias, known as sycophancy, manifests as a preference for user agreement over principled reasoning.<n>We introduce Beacon, a single-turn forced-choice benchmark that isolates this bias independent of conversational context.
  arXiv  Detail & Related papers  (2025-10-19T06:36:57Z)
• Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Models [7.18947815679122]
  Internal State Probing and Chain-of-Thought Verification are used to detect hallucinations in large language models.<n>We develop a unified framework that bridges the gap between the two methods.<n>Our framework consistently and significantly outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-10-13T15:31:21Z)
• Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning? [68.82210578851442]
  We investigate why safety alignment fails in reasoning models through a mechanistic interpretability lens.<n>Using a linear probing approach to trace refusal intentions across token positions, we discover a phenomenon termed as textbfrefusal cliff<n>We propose textbfCliff-as-a-Judge, a novel data selection method that identifies training examples exhibiting the largest refusal cliff to efficiently repair reasoning models' safety alignment.
  arXiv  Detail & Related papers  (2025-10-07T15:32:59Z)
• AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models [62.70575022567081]
  We propose AdvChain, an alignment paradigm that teaches models dynamic self-correction through adversarial CoT tuning.<n>Our work establishes a new direction for building more robust and reliable reasoning models.
  arXiv  Detail & Related papers  (2025-09-29T04:27:23Z)
• Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA [36.21980066799023]
  sycophancy is the tendency to align with user beliefs regardless of correctness.<n>Despite its importance, sycophancy remains underexamined in factual question answering contexts.<n>We introduce a unified evaluation framework to quantify the impact of sycophantic context on model behavior.
  arXiv  Detail & Related papers  (2025-08-19T11:30:52Z)
• Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI [60.142926537264714]
  We introduce the methodology of Faithfulness-through-Counterfactuals. It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation. It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
  arXiv  Detail & Related papers  (2022-05-25T03:40:59Z)
• Robustness and Accuracy Could Be Reconcilable by (Proper) Definition [109.62614226793833]
  The trade-off between robustness and accuracy has been widely studied in the adversarial literature. We find that it may stem from the improperly defined robust error, which imposes an inductive bias of local invariance. By definition, SCORE facilitates the reconciliation between robustness and accuracy, while still handling the worst-case uncertainty.
  arXiv  Detail & Related papers  (2022-02-21T10:36:09Z)
• Deconfounding Scores: Feature Representations for Causal Effect Estimation with Weak Overlap [140.98628848491146]
  We introduce deconfounding scores, which induce better overlap without biasing the target of estimation. We show that deconfounding scores satisfy a zero-covariance condition that is identifiable in observed data. In particular, we show that this technique could be an attractive alternative to standard regularizations.
  arXiv  Detail & Related papers  (2021-04-12T18:50:11Z)
• Superdeterministic hidden-variables models I: nonequilibrium and signalling [0.0]
  We first give an overview of superdeterminism and discuss various criticisms of it raised in the literature. We take up Bell's intuitive criticism that these models are conspiratorial'
  arXiv  Detail & Related papers  (2020-03-26T15:49:34Z)

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.