arXiv:2607. 18304v1 Announce Type: new Abstract: The sycophancy of large language models can increase the safety risk in intervention dialogue for autistic children.
arXiv:2608. 15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure.
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
Large language models (LLMs) exhibit sycophancy, a tendency to agree with user beliefs regardless of factual accuracy. This can reinforce misconceptions, but eliminating it entirely risks over-correction against valid opinions.
arXiv:2601. 02896v3 Announce Type: replace Abstract: Controlling emergent behavioral personas (e.
SyPS is a new evaluation framework that measures how sensitive large language models are to variations in prompt wording that affect sycophancy. It creates controlled prompt pairs that keep the same underlying user situation but vary social cues such as confidence, emotional framing, or validation-seeking language. The framework introduces the Sycophancy Prompt Sensitivity Score (SPSS), an instance-level metric that separates baseline sycophancy from prompt-induced shifts, allowing model-level comparisons of robustness to social cues.
The paper introduces Gated Activation Steering, an inference-time intervention that jointly mitigates hallucination and sycophancy in medical question answering. By learning separate steering directions from contrastive clinical pairs and applying them to specific attention heads, the method uses behavior‑specific gates to intervene only when needed. Experiments on EHR‑based clinical questions show that the 4‑billion‑parameter model with gated steering outperforms its unsteered counterpart and rivals larger models in resisting user pressure.
arXiv:2605. 21006v2 Announce Type: replace Abstract: We study the effect of different persona on \textbf{sycophancy}: model's agreement with users even when the user is incorrect.
arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).
arXiv:2602. 06941v2 Announce Type: replace-cross Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.
arXiv:2608. 13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants.
arXiv:2608.21377v1 Announce Type: cross Abstract: Sycophancy in large language models, the tendency to prioritize user agreement over truthful responses, has been documented extensively but studied p...
arXiv:2606. 13720v1 Announce Type: new Abstract: Arditi et al.