Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs

• URL: http://arxiv.org/abs/2509.21305v2
• Date: Fri, 26 Sep 2025 12:15:36 GMT
• Title: Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs
• Abstract summary: We decompose sycophantic agreement and sycophantic praise, contrasting both with genuine agreement.<n>Results suggest that sycophantic behaviors correspond to distinct, independently steerable representations.
• Score: 1.9693252204587723
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) often exhibit sycophantic behaviors -- such as excessive agreement with or flattery of the user -- but it is unclear whether these behaviors arise from a single mechanism or multiple distinct processes. We decompose sycophancy into sycophantic agreement and sycophantic praise, contrasting both with genuine agreement. Using difference-in-means directions, activation additions, and subspace geometry across multiple models and datasets, we show that: (1) the three behaviors are encoded along distinct linear directions in latent space; (2) each behavior can be independently amplified or suppressed without affecting the others; and (3) their representational structure is consistent across model families and scales. These results suggest that sycophantic behaviors correspond to distinct, independently steerable representations.

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)
• Dissociating the Internal Representations of Sycophancy in LLMs [9.383958408772694]
  Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect.<n>We train linear probes and construct steering vectors on activations of one subtype and evaluate their transfer to the other subtype to measure to what extent they share representations.<n>We find evidence that different LLMs represent these subtypes differently, with either more unified or more distinct and causally interfering representations.
  arXiv  Detail & Related papers  (2026-07-08T04:54:54Z)
• DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation [58.47973015036709]
  DisPOSE is a self-supervised framework that approximates the inherently discrete multi-view person-assignment problem.<n>By employing differentiable Sinkhorn projections during denoising, our model learns to guide solutions toward valid and feasible assignments.<n>The proposed approach outperforms current state-of-the-art self-supervised methods on standard datasets.
  arXiv  Detail & Related papers  (2026-06-05T16:14:39Z)
• From Packets to Patterns: Interpreting Encrypted Network Traffic as Longitudinal Behavioral Signals [2.8540604709894972]
  We test whether encrypted smartphone network traffic can passively capture behavioral patterns related to sleep, stress, and loneliness.<n>We model shared behavioral structure using a transformer backbone with per-user adapters.<n>We apply a sparse autoencoder to extract behavioral features corresponding to distinct patterns of activity.
  arXiv  Detail & Related papers  (2026-05-02T21:40:07Z)
• Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention [0.0]
  We introduce dual-stance evaluation, which tests both stances of each topic, and apply it to centroid-difference steering on Llama-3-8B-Instruct.<n>We find a dissociation: the model represents sycophantic and factual agreement in geometrically distinct subspaces, yet the steering direction projects equally onto both and cannot differentially target either.
  arXiv  Detail & Related papers  (2026-04-22T13:49:34Z)
• The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks [32.60957674853853]
  We study two recurring phenomena in Transformer language models.<n>Massive activations, in which a small number of tokens exhibit extreme outliers in a few channels, and attention sinks, in which certain tokens attract disproportionate attention mass regardless of semantic relevance.
  arXiv  Detail & Related papers  (2026-03-05T18:59:04Z)
• Disentangling Deception and Hallucination Failures in LLMs [7.906722750233381]
  We propose an internal, mechanism-oriented perspective that separates Knowledge Existence from Behavior Expression.<n> hallucination and deception correspond to two qualitatively different failure modes that may appear similar at the output level but differ in their underlying mechanisms.<n>We analyze these failure modes through representation separability, sparse interpretability, and inference-time activation steering.
  arXiv  Detail & Related papers  (2026-02-16T07:36:49Z)
• When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models [11.001042171551566]
  We study how user opinions induce sycophancy across different model families.<n>First-person prompts consistently induce higher sycophancy rates than third-person framings.<n>These findings highlight that sycophancy is not a surface-level artifact but emerges from a structural override of learned knowledge in deeper layers.
  arXiv  Detail & Related papers  (2025-08-04T05:55:06Z)
• Gumbel Counterfactual Generation From Language Models [64.55296662926919]
  We show that counterfactual reasoning is conceptually distinct from interventions.<n>We propose a framework for generating true string counterfactuals.<n>We show that the approach produces meaningful counterfactuals while at the same time showing that commonly used intervention techniques have considerable undesired side effects.
  arXiv  Detail & Related papers  (2024-11-11T17:57:30Z)
• Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality [84.94877848357896]
  Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. We analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity bias and the tendency to memorize whole examples. We show substantial empirical improvements using standard sequence-to-sequence models on two widely-used compositionality datasets.
  arXiv  Detail & Related papers  (2022-11-28T17:36:41Z)
• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective [72.55093886515824]
  We introduce a causal formalism of motion forecasting, which casts the problem as a dynamic process with three groups of latent variables. We devise a modular architecture that factorizes the representations of invariant mechanisms and style confounders to approximate a causal graph. Experiment results on synthetic and real datasets show that our three proposed components significantly improve the robustness and reusability of the learned motion representations.
  arXiv  Detail & Related papers  (2021-11-29T18:59:09Z)
• Classification and Adversarial examples in an Overparameterized Linear Model: A Signal Processing Perspective [10.515544361834241]
  State-of-the-art deep learning classifiers are highly susceptible to infinitesmal adversarial perturbations. We find that the learned model is susceptible to adversaries in an intermediate regime where classification generalizes but regression does not. Despite the adversarial susceptibility, we find that classification with these features can be easier than the more commonly studied "independent feature" models.
  arXiv  Detail & Related papers  (2021-09-27T17:35:42Z)
• Where and What? Examining Interpretable Disentangled Representations [96.32813624341833]
  Capturing interpretable variations has long been one of the goals in disentanglement learning. Unlike the independence assumption, interpretability has rarely been exploited to encourage disentanglement in the unsupervised setting. In this paper, we examine the interpretability of disentangled representations by investigating two questions: where to be interpreted and what to be interpreted.
  arXiv  Detail & Related papers  (2021-04-07T11:22:02Z)
• Do Generative Models Know Disentanglement? Contrastive Learning is All You Need [59.033559925639075]
  We propose an unsupervised and model-agnostic method: Disentanglement via Contrast (DisCo) in the Variation Space. DisCo achieves the state-of-the-art disentanglement given pretrained non-disentangled generative models, including GAN, VAE, and Flow.
  arXiv  Detail & Related papers  (2021-02-21T08:01:20Z)
• Disentangling Action Sequences: Discovering Correlated Samples [6.179793031975444]
  We demonstrate the data itself plays a crucial role in disentanglement and instead of the factors, and the disentangled representations align the latent variables with the action sequences. We propose a novel framework, fractional variational autoencoder (FVAE) to disentangle the action sequences with different significance step-by-step. Experimental results on dSprites and 3D Chairs show that FVAE improves the stability of disentanglement.
  arXiv  Detail & Related papers  (2020-10-17T07:37:50Z)
• Learning from Aggregate Observations [82.44304647051243]
  We study the problem of learning from aggregate observations where supervision signals are given to sets of instances. We present a general probabilistic framework that accommodates a variety of aggregate observations. Simple maximum likelihood solutions can be applied to various differentiable models.
  arXiv  Detail & Related papers  (2020-04-14T06:18:50Z)
• A Critical View of the Structural Causal Model [89.43277111586258]
  We show that one can identify the cause and the effect without considering their interaction at all. We propose a new adversarial training method that mimics the disentangled structure of the causal model. Our multidimensional method outperforms the literature methods on both synthetic and real world datasets.
  arXiv  Detail & Related papers  (2020-02-23T22:52:28Z)

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.