Ali Khalil

Ali khalil, Aly M. Kassem, Mohamed Abdelrazek et al.

We investigate whether harmful chain-of-thought (CoT) traces from compromised language models can transfer unsafe behaviour and be distilled into reusable jailbreak attacks. Using an emergent-misalignment organism and a refusal-ablated jailbroken organism, we transplant harmful CoTs into $29$ open-source and $5$ closed-source targets. Transferred traces raise harmful-response rates above $80\%$ on the most vulnerable open-source models, while semantically mismatched CoTs fail entirely. LLooM concept mining identifies four recurring components of harmful reasoning: proceduralisation, ethical decoupling, evasion, and target--vulnerability framing. Distilling these patterns into reusable system prompts produces effective black-box jailbreaks, outperforming direct CoT transplantation on strongly aligned models by up to an order of magnitude, including a $10\times$ improvement on GPT-4.1 AdvBench. Reasoning-enabled models are more than twice as vulnerable, and output-side safeguards such as Llama-Guard~3 frequently miss harmful generations. Our results show that harmful reasoning transfers at both the trace and pattern levels, motivating defences that evaluate reasoning context in addition to final outputs.

Omar Mahmoud, Ali Khalil, Buddhika Laknath Semage et al.

Hallucination in large language models (LLMs) has been widely studied in recent years, with progress in both detection and mitigation aimed at improving truthfulness. Yet, a critical side effect remains largely overlooked: enhancing truthfulness can negatively impact safety alignment. In this paper, we investigate this trade-off and show that increasing factual accuracy often comes at the cost of weakened refusal behavior. Our analysis reveals that this arises from overlapping components in the model that simultaneously encode hallucination and refusal information, leading alignment methods to suppress factual knowledge unintentionally. We further examine how fine-tuning on benign datasets, even when curated for safety, can degrade alignment for the same reason. To address this, we propose a method that disentangles refusal-related features from hallucination features using sparse autoencoders, and preserves refusal behavior during fine-tuning through subspace orthogonalization. This approach prevents hallucinations from increasing while maintaining safety alignment.We evaluate our method on commonsense reasoning tasks and harmful benchmarks (AdvBench and StrongReject). Results demonstrate that our approach preserves refusal behavior and task utility, mitigating the trade-off between truthfulness and safety.