Related papers: Beyond "I cannot fulfill this request": Alleviatin…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Multimodal large language models (MLLMs) have become the cornerstone of today's generative AI ecosystem, sparking intense competition among tech giants and startups. In particular, an MLLM generates a text response given a prompt consisting…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

In the multi-turn interaction schema, large language models (LLMs) can leverage user feedback to enhance the quality and relevance of their responses. However, evaluating an LLM's ability to incorporate user refutation feedback is crucial…

With the growing adoption of Large Language Models (LLMs) in critical areas, ensuring their security against jailbreaking attacks is paramount. While traditional defenses primarily rely on refusing malicious prompts, recent logit-level…

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

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…

Many safety post-training methods for large language models (LLMs) are designed to modify the model's behaviour from producing unsafe answers to issuing refusals. However, such distribution shifts are often brittle and degrade performance…

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…

Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly…

In LLM-based text-to-SQL systems, unanswerable and underspecified user queries may generate not only incorrect text but also executable programs that yield misleading results or violate safety constraints, posing a major barrier to safe…

Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass…

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Recent advancements in Large Language Models (LLMs) have significantly enhanced interactions between users and models. These advancements concurrently underscore the need for rigorous safety evaluations due to the manifestation of social…

The swift advancement in the scales and capabilities of Large Language Models (LLMs) positions them as promising tools for a variety of downstream tasks. In addition to the pursuit of better performance and the avoidance of violent feedback…

A key component of building safe and reliable language models is enabling the models to appropriately refuse to follow certain instructions or answer certain questions. We may want models to output refusal messages for various categories of…

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…

The capacity of large language models (LLMs) to generate honest, harmless, and helpful responses heavily relies on the quality of user prompts. However, these prompts often tend to be brief and vague, thereby significantly limiting the full…

Large Language Models (LLMs) have demonstrated strong reasoning capabilities across various tasks. However, even minor variations in query phrasing, despite preserving the underlying semantic meaning, can significantly affect their…

This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…