相关论文: Characterizing Selective Refusal Bias in Large Lan…
The conformity bias exhibited by large language models (LLMs) can pose a significant challenge to decision-making in LLM-based multi-agent systems (LLM-MAS). While many prior studies have treated "conformity" simply as a matter of opinion…
Large Language Models (LLMs) are increasingly integrated into critical decision-making processes, such as loan approvals and visa applications, where inherent biases can lead to discriminatory outcomes. In this paper, we examine the nuanced…
Large Language Models (LLMs) have been shown to generate harmful content. However, the underlying causes of such behavior remain under explored. We propose a causal mediation analysis-based approach to identify the causal factors…
Large language models (LLMs) have rapidly become indispensable tools for acquiring information and supporting human decision-making. However, ensuring that these models uphold fairness across varied contexts is critical to their safe and…
Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety…
Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…
The trend towards large language models (LLMs) for guardrailing against undesired behaviors is increasing and has shown promise for censoring user inputs. However, increased latency, memory consumption, hosting expenses and non-structured…
Large Language Models (LLMs) like GPT-4 and Gemini have significantly advanced artificial intelligence by enabling machines to generate and comprehend human-like text. Despite their impressive capabilities, LLMs are not immune to…
As large language models (LLMs) have been deployed in various real-world settings, concerns about the harm they may propagate have grown. Various jailbreaking techniques have been developed to expose the vulnerabilities of these models and…
Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause significant harm. However, evaluating the fairness of models is…
Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety…
Large Language Models (LLMs) are trained on large corpora written by humans and demonstrate high performance on various tasks. However, as humans are susceptible to cognitive biases, which can result in irrational judgments, LLMs can also…
We introduce a lightweight yet highly effective safety guardrail framework for language models, demonstrating that small-scale language models can achieve, and even surpass, the performance of larger counterparts in content moderation…
Large Language Models (LLMs) have been demonstrated to generate illegal or unethical responses, particularly when subjected to "jailbreak." Research on jailbreak has highlighted the safety issues of LLMs. However, prior studies have…
The rapid advancement of large language models (LLMs) has brought significant benefits to various domains while introducing substantial risks. Despite being fine-tuned through reinforcement learning, LLMs lack the capability to discern…
The widespread application of Large Language Models (LLMs) involves ethical risks for users and societies. A prominent ethical risk of LLMs is the generation of unfair language output that reinforces or exacerbates harm for members of…
Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In this context, safety is no longer about blocking harmful…
While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…
Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions worldwide. As they become integrated into everyday tasks, growing reliance on their outputs raises significant concerns. In…
Large language models (LLMs) increasingly operate in high-stakes settings including healthcare and medicine, where demographic attributes such as race and ethnicity may be explicitly stated or implicitly inferred from text. However,…