It is shown that persistent sycophancy reduction does not guarantee stronger direct refusal, while identifying recovery under user pressure as a distinct, conditional benefit of training intervention.
Abstract
Reliable refusal of harmful requests is essential to the safe deployment of language models. Because excessive eagerness to please users may undermine existing refusal capabilities, reducing sycophancy offers a potential route to stronger refusal beyond the harmful scenarios covered by safety training. We investigate this possibility using compensatory feature injection (CFI), a training technique designed to limit the acquisition of a target concept by supplying its associated activation during learning. Across three Qwen3.5 base models, we use sparse autoencoders (SAEs) to identify the top-ranked sycophancy feature from paired sycophantic and independent responses, then validate its behavioral influence through inference steering. We subsequently inject the selected feature during supervised fine-tuning on sycophantic targets. Positive injection reduces learned sycophancy after removal (by 62.0% relative to ordinary fine-tuning in 35B-A3B), whereas modest negative injection increases it. Unexpectedly, these reductions in sycophancy do not consistently improve direct refusal of harmful requests, motivating a narrower evaluation of the same harmful intents under user pressure. In this setting, ordinary fine-tuning on sycophantic responses substantially weakens refusal, while selected checkpoints trained with positive injection recover part of the loss, including approximately 95% in 35B-A3B. These findings show that persistent sycophancy reduction does not guarantee stronger direct refusal, while identifying recovery under user pressure as a distinct, conditional benefit of training intervention.
Refusal-Enhanced INhibitory Steering is proposed, which suppresses harmful continuation features and enhances safe refusal features in the same SAE feature space, and substantially reduces harmful responses, markedly improves safe refusals and largely preserves general capabilities.
Kai-Xuan Ding, Hao-Yang Xu, Jihua Peng et al.· 0 citations
SSRFT shows substantially greater robustness to prefilling attacks and better generalization to unseen jailbreak domains, while reducing over-refusal on benign queries and preserving the model's general capabilities, establishing safe-role internalization as an effective alternative to refusal-centric safety alignment.
Jin-Hao Pang, Jitai Hao, Qiang Huang et al.· 0 citations
This work proposes an explanation-aware safety framework that augments binary harmfulness detection with structured, human-interpretable explanations capturing severity, strategies, trigger spans, ratio-nales, and derived safety factors, and introduces a human–LLM hybrid annotation and canonicaliza-tion pipeline.
Sunghee Dong, Sungwon Yi, K. Bae et al.· Proceedings of the Thirty-Fi...· 0 citations
Experimental results demonstrate that RISA improves refusal reliability while largely preserving model utility, offering a practical solution for response-aware refusal calibration in LLMs.
Wenhan Chang, Tian-Qing Zhu, P. Xiong et al.· 0 citations
DeShortcut-Align is proposed, a shortcut-decoupling alignment framework that reduces dependence on superficial cues that significantly improves robustness against template-stripping bypass attacks, substantially reduces over-refusal, and better preserves general-purpose reasoning capabilities, thereby mitigating the al...
Qi-Rui Liu, Yi-Chen Sun, Yan Wang et al.· arXiv.org· 2 citations
The results support a circuit-level interpretation of LLM safety and suggest that mechanistic abstractions can reveal stable and transferable patterns underlying aligned behavior.
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.