相关论文: Reverse Constitutional AI: A Framework for Control…

Deep learning models have shown promising predictive accuracy for time-series healthcare applications. However, ensuring the robustness of these models is vital for building trustworthy AI systems. Existing research predominantly focuses on…

Large Language Models (LLMs) have shown significant advances in text generation but often lack the reliability needed for autonomous deployment in high-stakes domains like healthcare, law, and finance. Existing approaches rely on external…

Compound AI Systems (CAIS) are an emerging paradigm that integrates large language models (LLMs) with external components, including retrievers, agents, tools, and orchestrators, to overcome the limitations of standalone models in tasks…

Generative language models are increasingly used for contract drafting and enhancement, creating a scenario where competing parties deploy different language models against each other. This introduces not only a game-theory challenge but…

A critical challenge remains unresolved as generative AI systems are quickly implemented in various organizational settings. Despite significant advances in memory components such as RAG, vector stores, and LLM agents, these systems still…

Explainable AI (XAI) and interpretable machine learning methods help to build trust in model predictions and derived insights, yet also present a perverse incentive for analysts to manipulate XAI metrics to support pre-specified…

Agentic Generative AI, powered by Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG), Knowledge Graphs (KGs), and Vector Stores (VSs), represents a transformative technology applicable to specialized domains such as…

Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. We present RAID (Refusal-Aware and Integrated Decoding), a framework that…

Legal research is a crucial task in the practice of law. It requires intense human effort and intellectual prudence to research a legal case and prepare arguments. Recent boom in generative AI has not translated to proportionate rise in…

A red team simulates adversary attacks to help defenders find effective strategies to defend their systems in a real-world operational setting. As more enterprise systems adopt AI, red-teaming will need to evolve to address the unique…

AI safety via debate and reinforcement learning from AI feedback (RLAIF) are both proposed methods for scalable oversight of advanced AI systems, yet no formal framework relates them or characterizes when debate offers an advantage. We…

A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack…

The convergence of AI and 6G network automation introduces new challenges in maintaining transparency, fairness, and accountability across multivendor management systems. Although closed-loop AI orchestration improves adaptability and…

This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a 'backdoor poisoning' attack on NLP models. Our poisoning attack utilizes conditional…

The evolution of Large Language Models (LLMs) and the software agents built on them (AI agents) marks a turning point in the transition from a human-centric Web to an ``Agentic Web'' driven by AI agents. However, for AI-Generated Content…

The constitutional framework of alignment aims to align large language models (LLMs) with value-laden principles written in natural language (such as to avoid using biased language). Prior work has focused on parameter fine-tuning…

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Until recently, robotics safety research was predominantly about collision avoidance and hazard reduction in the immediate vicinity of a robot. Since the advent of large vision and language models (VLMs), robots are now also capable of…

Large language models (LLMs) trained on unfiltered corpora inherently risk retaining sensitive information, necessitating selective knowledge unlearning for regulatory compliance and ethical safety. However, existing parameter-modifying…

Medical Large Language Models (LLMs) are increasingly deployed for clinical decision support across diverse specialties, yet systematic evaluation of their robustness to adversarial misuse and privacy leakage remains inaccessible to most…