相关论文: TRACEALIGN -- Tracing the Drift: Attributing Align…

Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods typically rely on superficial pass/fail signals, offering limited visibility into program…

Requirements traceability, the process of establishing and maintaining relationships between requirements and various software development artifacts, is paramount for ensuring system integrity and fulfilling requirements throughout the…

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer…

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training…

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

With the rapid development of large language models (LLMs), aligning LLMs with human values and societal norms to ensure their reliability and safety has become crucial. Reinforcement learning with human feedback (RLHF) and Constitutional…

Misalignment in Large Language Models (LLMs) arises when model behavior diverges from human expectations and fails to simultaneously satisfy safety, value, and cultural dimensions, which must co-occur in real-world settings to solve a…

Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in…

As large language models (LLMs) are trained on massive datasets, they have raised significant privacy and ethical concerns due to their potential to inadvertently retain sensitive information. Unlearning seeks to selectively remove specific…

The rapid integration of Large Language Models (LLMs) into educational assessment rests on the unverified assumption that instruction following capability translates directly to objective adjudication. We demonstrate that this assumption is…

Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length. To address this, we present LongAlign -- a recipe of the instruction data, training, and evaluation…

Misalignment in Large Language Models (LLMs) refers to the failure to simultaneously satisfy safety, value, and cultural dimensions, leading to behaviors that diverge from human expectations in real-world settings where these dimensions…

LLMs are an integral component of retrieval-augmented generation (RAG) systems. While many studies focus on evaluating the overall quality of end-to-end RAG systems, there is a gap in understanding the appropriateness of LLMs for the RAG…

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 Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this…

Learning analytics researchers often analyze qualitative student data such as coded annotations or interview transcripts to understand learning processes. With the rise of generative AI, fully automated and human-AI workflows have emerged…

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Language models trained on large-scale corpus often generate content that is harmful, toxic, or contrary to human preferences, making their alignment with human values a critical concern. Reinforcement learning from human feedback (RLHF)…

The alignment problem refers to concerns regarding powerful intelligences, ensuring compatibility with human preferences and values as capabilities increase. Current large language models (LLMs) show misaligned behaviors, such as strategic…