Dissociating the Internal Representations of Sycophancy in LLMs

• URL: http://arxiv.org/abs/2607.07003v1
• Date: Wed, 08 Jul 2026 04:54:54 GMT
• Title: Dissociating the Internal Representations of Sycophancy in LLMs
• Abstract summary: 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.
• Score: 9.383958408772694
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect. While sycophancy is often treated as a single defined behavior, it can manifest in substantially distinct ways and circumstances, raising the question of whether this multi-faceted nature is reflected in its internal mechanisms. To address this gap, we dissociate the representations of sycophancy into factual and opinion subtypes -- motivated by the distinction between verifiable claims and subjective beliefs. 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. We find evidence that different LLMs represent these subtypes differently, with either more unified or more distinct and causally interfering representations. This method of dissociation offers a promising framework for studying the representational structure of complex model behaviors.

Related papers

• CV-DCLR: Causal-Visual Dynamic Label Refinement for Robust Zero-Shot Learning [25.21342780360303]
  We propose the Causal-Visual Dynamic Label Refinement framework.<n>It recalibrates visual-semantic associations via a Dual-Stream Mutual Correction Mechanism.<n>Experiments on the CUB, SUN, and AWA2 benchmarks demonstrate that CV-DCLR significantly outperforms state-of-the-art methods in high-ambiguity scenarios.
  arXiv  Detail & Related papers  (2026-07-01T12:45:35Z)
• Constrained latent state modeling: A unifying perspective on representation learning under competing constraints [0.6496997624776696]
  Learning latent representations from complex data is central to modern machine learning.<n>Current approaches remain fragmented, relying on distinct -- and often implicit -- assumptions about what these states should represent.<n>We argue that latent representations are typically learned from underconstrained objectives that fail to specify the properties that meaningful latent states should satisfy.
  arXiv  Detail & Related papers  (2026-05-15T14:25:40Z)
• 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)
• Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models [77.98801218316505]
  Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning.<n>We investigate the internal processing of LLMs during in-context concept inference.
  arXiv  Detail & Related papers  (2026-02-08T03:14:39Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs [1.9693252204587723]
  We decompose sycophantic agreement and sycophantic praise, contrasting both with genuine agreement.<n>Results suggest that sycophantic behaviors correspond to distinct, independently steerable representations.
  arXiv  Detail & Related papers  (2025-09-25T15:19:39Z)
• How do Transformers Learn Implicit Reasoning? [67.02072851088637]
  We study how implicit multi-hop reasoning emerges by training transformers from scratch in a controlled symbolic environment.<n>We find that training with atomic triples is not necessary but accelerates learning, and that second-hop generalization relies on query-level exposure to specific compositional structures.
  arXiv  Detail & Related papers  (2025-05-29T17:02:49Z)
• The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology [4.280045926995889]
  This study focuses on how adversarial inputs systematically affect the internal representation spaces of Large Language Models.<n>By quantifying the shape of activations and neuronal information flow, our architecture-agnostic framework reveals fundamental invariants of representational change.
  arXiv  Detail & Related papers  (2025-05-26T18:31:49Z)
• Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning [80.44084021062105]
  We propose a novel latent partial causal model for multimodal data, featuring two latent coupled variables, connected by an undirected edge, to represent the transfer of knowledge across modalities.<n>Under specific statistical assumptions, we establish an identifiability result, demonstrating that representations learned by multimodal contrastive learning correspond to the latent coupled variables up to a trivial transformation.<n>Experiments on a pre-trained CLIP model embodies disentangled representations, enabling few-shot learning and improving domain generalization across diverse real-world datasets.
  arXiv  Detail & Related papers  (2024-02-09T07:18:06Z)
• Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning [75.46664770669949]
  We present relation-aware contrastive self-supervised learning (ReCo) to integrate instance relations. Our ReCo consistently gains remarkable performance improvements.
  arXiv  Detail & Related papers  (2022-11-02T03:25:28Z)
• 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)
• Structural Causal Models Are (Solvable by) Credal Networks [70.45873402967297]
  Causal inferences can be obtained by standard algorithms for the updating of credal nets. This contribution should be regarded as a systematic approach to represent structural causal models by credal networks. Experiments show that approximate algorithms for credal networks can immediately be used to do causal inference in real-size problems.
  arXiv  Detail & Related papers  (2020-08-02T11:19:36Z)

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.