相关论文: BeaverTails: Towards Improved Safety Alignment of …

Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs). However, achieving authentic alignment…

Alignment research on large language models (LLMs) increasingly depends on understanding how these systems are used in everyday contexts. Yet naturalistic interaction data is difficult to access due to privacy constraints and platform…

Numerous medical systems powered by Large Language Models (LLMs) have achieved remarkable progress in diverse healthcare tasks. However, research on their medication safety remains limited due to the lack of real world datasets, constrained…

Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid…

Safety for Large Language Models (LLMs) has been an ongoing research focus since their emergence and is even more relevant nowadays with the increasing capacity of those models. Currently, there are several guardrails in place for all…

In the era of increasingly sophisticated natural language processing (NLP) systems, large language models (LLMs) have demonstrated remarkable potential for diverse applications, including tasks requiring nuanced textual understanding and…

The growing demand for accessible mental health support, compounded by workforce shortages and logistical barriers, has led to increased interest in utilizing Large Language Models (LLMs) for scalable and real-time assistance. However,…

Annotating speaker attributes from text is inherently ambiguous, particularly in multilingual settings where demographic and social cues are implicit and culturally variable. We propose a human-large language model (LLM) collaborative…

Large Language Models (LLMs) have demonstrated remarkable performance across various natural language tasks, marking significant strides towards general artificial intelligence. While general artificial intelligence is leveraged by…

Large Language Models (LLMs), when used in educational settings without pedagogical fine-tuning, often provide immediate answers rather than guiding students through the problem-solving process. This approach falls short of pedagogically…

As the number of large language models (LLMs) released to the public grows, there is a pressing need to understand the safety implications associated with these models learning from third-party custom finetuning data. We explore the…

Large language models (LLMs) have demonstrated outstanding performance in natural language processing tasks. However, in the field of recommender systems, due to the inherent structural discrepancy between user behavior data and natural…

In this paper, we explore the feasibility of leveraging large language models (LLMs) to automate or otherwise assist human raters with identifying harmful content including hate speech, harassment, violent extremism, and election…

Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches,…

Large language models (LLMs) are often assumed to contain ``safety regions'' -- parameter subsets whose modification directly influences safety behaviors. We conduct a systematic evaluation of four safety region identification methods…

As large language models (LLMs) transition from research prototypes to production systems, practitioners often need reliable methods to verify model outputs and characterize tail risk for safe deployment. While sampling-based estimates…

The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models…

Understanding how large language models (LLMs) process emotionally sensitive content is critical for building safe and reliable systems, particularly in mental health contexts. We investigate the scaling behavior of LLMs on two key tasks:…

Controversy is a reflection of our zeitgeist, and an important aspect to any discourse. The rise of large language models (LLMs) as conversational systems has increased public reliance on these systems for answers to their various…

Building safe Large Language Models (LLMs) across multiple languages is essential in ensuring both safe access and linguistic diversity. To this end, we conduct a large-scale, comprehensive safety evaluation of the current LLM landscape.…