Related papers: Language Models are Homer Simpson! Safety Re-Align…
Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. While several defenses have been proposed, our…
Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…
Scientific software relies on high-precision computation, yet finite floating-point representations can introduce precision errors that propagate in safety-critical domains. Despite the growing use of large language models (LLMs) in…
Most safety evaluations of large language models (LLMs) remain anchored in English. Translation is often used as a shortcut to probe multilingual behavior, but it rarely captures the full picture, especially when harmful intent or structure…
Reverse engineering (RE) of x86 binaries is indispensable for malware and firmware analysis, but remains slow due to stripped metadata and adversarial obfuscation. Large Language Models (LLMs) offer potential for improving RE efficiency…
Large language models (LLMs) have made significant advancements across various tasks, but their safety alignment remain a major concern. Exploring jailbreak prompts can expose LLMs' vulnerabilities and guide efforts to secure them. Existing…
Large language models demonstrate impressive proficiency in language understanding and generation. Nonetheless, training these models from scratch, even the least complex billion-parameter variant demands significant computational resources…
Recent advances show that large language models (LLMs) generalize strong performance across different natural language benchmarks. However, the large size of LLMs makes training and inference expensive and impractical to run in…
Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and resource-conserving approach would be continual…
Mitigating explicit and implicit biases in Large Language Models (LLMs) has become a critical focus in the field of natural language processing. However, many current methodologies evaluate scenarios in isolation, without considering the…
Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and…
The rapid advancement of Large Language Models (LLMs) in the realm of mathematical reasoning necessitates comprehensive evaluations to gauge progress and inspire future directions. Existing assessments predominantly focus on problem-solving…
Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…
Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models generate harmful responses when faced with malicious prompts.…
We present a new method LiST is short for Lite Prompted Self-Training for parameter-efficient fine-tuning of large pre-trained language models (PLMs) for few-shot learning. LiST improves over recent methods that adopt prompt-based…
Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…
Despite the remarkable proficiency of \textit{Large Reasoning Models} (LRMs) in handling complex reasoning tasks, their reliability in safety-critical scenarios remains uncertain. Existing evaluations primarily assess response-level safety,…
LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore…
Detecting life-threatening language is essential for safeguarding individuals in distress, promoting mental health and well-being, and preventing potential harm and loss of life. This paper presents an effective approach to identifying…
Large language models (LLMs) have shown promise for event log analysis, but their high computational requirements, reliance on cloud infrastructure, and security concerns limit practical deployment. In addition, most existing approaches…