相关论文: Matching Ranks Over Probability Yields Truly Deep …

Large Language Models (LLMs) are increasingly evaluated on multiple-choice question answering (MCQA) tasks using *first-token probability* (FTP), which selects the answer option whose initial token has the highest likelihood. While…

Supervised fine-tuning (SFT) is a fundamental post-training strategy to align Large Language Models (LLMs) with human intent. However, traditional SFT often ignores the one-to-many nature of language by forcing alignment with a single…

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…

Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a small…

Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs) by enabling audio-based human interactions. However, recent research has revealed that LALMs remain vulnerable to harmful queries due to…

Recent alignment studies commonly remove introductory boilerplate phrases from supervised fine-tuning (SFT) datasets. This work challenges that assumption. We hypothesize that safety- and reasoning-oriented prefix sentences serve as…

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine…

Existing LLMs-post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT). Each paradigm presents a distinct trade-off: (1) SFT excels at mimicking demonstration data, but can lead…

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks…

We address the problem of making a pre-trained reinforcement learning (RL) policy safety-aware by incorporating cost constraints without retraining it from scratch. While costs could be numerically encoded, we assume a more general setting…

Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…

Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats,…

Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests.…

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse propensity scoring to…

Reasoning-capable LLMs have achieved major breakthroughs in solving complex problems, but recent work shows that acquiring and deploying strong reasoning can introduce significant safety risks. A common mitigation is to apply a secondary…

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…