Related papers: From Parameter Dynamics to Risk Scoring : Quantify…

Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acquired capabilities. Recent evidence suggests that this phenomenon is primarily driven by…

While the safety risks of image-based large language models (Image LLMs) have been extensively studied, their video-based counterparts (Video LLMs) remain critically under-examined. To systematically study this problem, we introduce…

Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing susceptibility to…

Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously through provider-side updates without explicit version changes. These silent updates can…

Fine-tuning large language models (LLMs) has become essential for adapting pretrained models to specific downstream tasks. In this paper, we propose Linear Chain Transformation (LinChain), a novel approach that introduces a sequence of…

In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through…

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…

Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination (test set exposure during training) risk masking true generalization. This concern extends to…

Large Language Model (LLM) alignment conventionally relies on supervised fine-tuning or reinforcement learning based alignment frameworks. These methods typically require labeled or preference datasets and involve updating model weights to…

Driven by privacy protection laws and regulations, unlearning in Large Language Models (LLMs) is gaining increasing attention. However, current research often neglects the interpretability of the unlearning process, particularly concerning…

The pursuit of leaderboard rankings in Large Language Models (LLMs) has created a fundamental paradox: models excel at standardized tests while failing to demonstrate genuine language understanding and adaptability. Our systematic analysis…

The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison. Yet, their reliability is increasingly questioned due to sensitivity to shallow…

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

Safety alignment is essential for the responsible deployment of large language models (LLMs). Yet, existing approaches often rely on heavyweight fine-tuning that is costly to update, audit, and maintain across model families. Full…

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by…

There are two primary ways of incorporating new information into a language model (LM): changing its prompt or changing its parameters, e.g. via fine-tuning. Parameter updates incur no long-term storage cost for model changes. However, for…

Autonomous control systems face significant challenges in performing complex tasks in the presence of latent risks. To address this, we propose an integrated framework that combines Large Language Models (LLMs), numerical optimization, and…

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom…

Memorization in Large Language Models (LLMs) poses privacy and security risks, as models may unintentionally reproduce sensitive or copyrighted data. Existing analyses focus on average-case scenarios, often neglecting the highly skewed…

Recent research demonstrates that the nascent fine-tuning-as-a-service business model exposes serious safety concerns: fine-tuning with a few harmful data uploaded from the users can compromise the safety alignment of the model. The attack,…