相关论文: NeMo Guardrails: A Toolkit for Controllable and Sa…

Machine learning (ML), especially with the emergence of large language models (LLMs), has significantly transformed various industries. However, the transition from ML model prototyping to production use within software systems presents…

Human guidance in reinforcement learning (RL) is often impractical for large-scale applications due to high costs and time constraints. Large Language Models (LLMs) offer a promising alternative to mitigate RL sample inefficiency and…

We present Wildflare GuardRail, a guardrail pipeline designed to enhance the safety and reliability of Large Language Model (LLM) inferences by systematically addressing risks across the entire processing workflow. Wildflare GuardRail…

Deploying language models (LMs) necessitates outputs to be both high-quality and compliant with safety guidelines. Although Inference-Time Guardrails (ITG) offer solutions that shift model output distributions towards compliance, we find…

The use of large language models (LLMs) in natural language processing (NLP) tasks is rapidly increasing, leading to changes in how researchers approach problems in the field. To fully utilize these models' abilities, a better understanding…

Generative AI is increasingly important in software engineering, including safety engineering, where its use ensures that software does not cause harm to people. This also leads to high quality requirements for generative AI. Therefore, the…

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation…

Recent large language models (LLMs) have demonstrated promising capabilities in modeling real-world knowledge and enhancing knowledge-based generation tasks. In this paper, we further explore the potential of using LLMs to aid in the design…

Large Language Models (LLMs) are currently being integrated into industrial software applications to help users perform more complex tasks in less time. However, these LLM-Integrated Applications (LIA) expand the attack surface and…

Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each training question to a single response language or rely on a fixed dominant language for…

Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…

Interaction with Large Language Models (LLMs) is primarily carried out via prompting. A prompt is a natural language instruction designed to elicit certain behaviour or output from a model. In theory, natural language prompts enable…

As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In…

The integration of Large Language Models (LLMs) into Development Environments (IDEs) has become a focal point in modern software development. LLMs such as OpenAI GPT-3.5/4 and Code Llama offer the potential to significantly augment…

The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…

Large Language Models (LLMs) are compact representations of all public knowledge of our physical environment and animal and human behaviors. The application of LLMs to robotics may offer a path to highly capable robots that perform well…

The introduction of large language models (LLMs) has greatly enhanced the capabilities of software agents. Instead of relying on rule-based interactions, agents can now interact in flexible ways akin to humans. However, this flexibility…

Conversational agents based on Large Language Models (LLMs) have recently emerged as powerful tools for human-computer interaction. Nevertheless, their black-box nature implies challenges in predictability and a lack of personalization,…

Large language model (LLM) reading assistants are increasingly used in settings that require interpretation rather than simple retrieval. In these contexts, the central risk is not only error or unsafe output, but interpretive displacement:…

Recent research explores optimization using large language models (LLMs) by either iteratively seeking next-step solutions from LLMs or directly prompting LLMs for an optimizer. However, these approaches exhibit inherent limitations,…