Large Language Models (LLMs) exhibit sycophancy, aligning with user assertions even when they conflict with facts. We frame sycophancy as a sociolinguistic phenomenon, disentangling explicit authority (credentials) from implicit authority (linguistic register), and adopt the Sycophancy Matrix, an adversarial evaluation framework that isolates these variables. Evaluating open-weight models on a controlled TruthfulQA subset across English, Spanish, and Portuguese cultural variants, we find that models exhibit statistically significant cultural variation and show stable sycophancy fingerprints intrinsic to model family, independent of language. We then recast the Matrix as a defence framework, evaluating two activation steering methods, CAA and NoLAI, on whether methods trained on English transfer to Italian, Spanish, and Portuguese. Both methods reduce the Weighted Sycophancy Rate across all four attack styles, and the defence generalises cross-lingually: sociolinguistic stance, its emergence, and its correction are encoded in a largely language-agnostic geometric space.

Large Language Models (LLMs) have been shown to exhibit sycophancy, a tendency to align with user assertions even when they conflict with facts. We frame sycophancy as a sociolinguistic phenomenon, disentangling two distinct drivers of credibility: explicit authority (credentials) and implicit authority (linguistic register). We introduce the Sycophancy Matrix, an adversarial evaluation framework that isolates these variables. Using a controlled subset of TruthfulQA, we evaluate open-weight models across English, Spanish, and Portuguese variants. Our findings reveal that models often conflate high register with truthfulness: for some architectures, sophisticated tone triggers deference more effectively than explicit expertise. Furthermore, we observe statistically significant variability across cultural variants of Spanish and Portuguese, supporting the hypothesis that LLMs internalise language-specific sociolinguistic norms and that sycophancy is not a purely technical deficit but an emergent property of multilingual training and alignment. Finally, we identify stable sycophancy fingerprints–domain-specific vulnerability profiles that persist across languages–suggesting that alignment artefacts are intrinsic to model families rather than linguistic context.

LLMs often struggle with deductive judgement in syllogistic reasoning, systematically conflating semantic plausibility with formal validity—a phenomenon known as content effect. This bias persists even when models generate step-wise explanations, indicating that intermediate rationales may inherit the same semantic shortcuts that affect answers. Recent approaches mitigate this issue by increasing inference-time structural constraints, either by encouraging abstract intermediate representations or by intervening in the model’s internal computations; yet, reliably suppressing semantic interference remains an open challenge.

To make formal deduction less sensitive to semantic content, we introduce a framework for abstraction-guided reasoning that separates structural inference from lexical semantics. We construct paired content-laden and abstract syllogisms and use the model’s activations on abstract inputs to define an abstract reasoning space. We then learn lightweight Abstractors that, from content-conditioned residual-stream states, predict representations aligned with this space and integrate these predictions via multi-layer interventions during the forward pass. Using cross-lingual transfer as a test bed, we show that abstraction-aligned steering reduces content-driven errors and improves validity-sensitive performance. Our results position activation-level abstraction as a scalable mechanism for enhancing the robustness of formal reasoning in LLMs against semantic interference.

Large Language Models (LLMs) often struggle with formal logical reasoning, frequently conflating content plausibility with logical validity. This well-known content effect undermines their capacity to act as reliable deductive reasoners, particularly in multilingual contexts where both linguistic variability and world knowledge may deepen biases. Prior work shows that prompting and tuning interventions can alleviate these issues only partially, leaving models vulnerable to semantic interference.While previous studies have explored activation steering and other test-time interventions, this work has focused predominantly on English.To make reasoning more consistent, robust, and transferable across languages, we investigate the use of activation steering—an inference-time intervention that modulates internal representations towards a cross-lingual reasoning space. Our experiments demonstrate that steering techniques constructed for English-based syllogisms generalise effectively to multilingual datasets, yielding higher formal reasoning accuracy (up to +36%) while minimally affecting language modelling performance. Moreover, steering supports partial transfer to out-of-distribution tasks, highlighting its potential as a scalable mechanism for cross-lingual transferable reasoning. These findings advance the prospect of developing LLMs that can serve as reliable soft reasoners across language landscapes.