# Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution

arXiv: https://arxiv.org/abs/2602.04918 · HTML: https://mlsanity.com/paper/2602.04918/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 18 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 17 of 17)

- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Simple synthetic data reduces sycophancy in large language models](https://mlsanity.com/paper/2308.03958/) (2023)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models](https://mlsanity.com/paper/2508.02087/) (2025)
- [The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions](https://mlsanity.com/paper/2502.09674/) (2025)
- [Sycophancy Hides Linearly in the Attention Heads](https://mlsanity.com/paper/2601.16644/) (2026)
- [Analysing the Residual Stream of Language Models Under Knowledge Conflicts](https://mlsanity.com/paper/2410.16090/) (2024)
- [An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression](https://mlsanity.com/paper/2504.18433/) (2025)
- [The Geometries of Truth Are Orthogonal Across Tasks](https://mlsanity.com/paper/2506.08572/) (2025)
- [Geometry of Decision Making in Language Models](https://mlsanity.com/paper/2511.20315/) (2025)
- [Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models](https://mlsanity.com/paper/2601.09445/) (2026)
- [Unlocking In-Context Learning for Natural Datasets Beyond Language Modelling](https://mlsanity.com/paper/2501.06256/) (2025)

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

- [Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts](https://mlsanity.com/paper/2610.20067/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) frequently prioritize conflicting in-context information over pre-existing parametric memory, a phenomenon often termed sycophancy or compliance. However, the mechanistic realization of this behavior remains obscure, specifically how the model resolves these knowledge conflicts through compliance, and whether this suppression arises from signal magnitude dilution or directional geometric alteration within the residual stream. To resolve this, we conducted a layer-wise geometric analysis across Qwen-3-4B, Llama-3.1-8B, and GLM-4-9B, decomposing the residual stream updates induced by counter-factual contexts into radial (norm-based) and angular (cosine-based) components. Our empirical results reject the universality of the "Manifold Dilution" hypothesis, as two of the three architectures maintained stable residual norms despite exhibiting significant performance degradation on factual queries. Instead, we observed that compliance is consistently characterized by "Orthogonal Interference," where the conflicting context injects a steering vector that is quasi-orthogonal to the ground-truth direction, effectively rotating the hidden state representation. This suggests that models do not "unlearn" or suppress the magnitude of internal truths but rather employ a mechanism of geometric displacement to bypass the correct unembedding vector, effectively simulating adoption while preserving the original structural magnitude. These findings challenge scalar confidence metrics for detecting hallucinations and underscore the necessity of vectorial monitoring to distinguish between genuine knowledge integration and superficial in-context mimicry.