相关论文: STAR: SocioTechnical Approach to Red Teaming Langu…

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) systems in diverse target domains, such as noise and accents.…

Ensuring the safe deployment of AI systems is critical in industry settings where biased outputs can lead to significant operational, reputational, and regulatory risks. Thorough evaluation before deployment is essential to prevent these…

Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving. However, malicious agents in MAS may inject misinformation…

This work presents STAR, the first end-to-end speech-to-audio generation framework, designed to enhance efficiency and address error propagation inherent in cascaded systems. Unlike prior approaches relying on text or vision, STAR leverages…

Large Language Model (LLM) safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine learning and AI safety, safeguard red teaming has…

Recent work has proposed automated red-teaming methods for testing the vulnerabilities of a given target large language model (LLM). These methods use red-teaming LLMs to uncover inputs that induce harmful behavior in a target LLM. In this…

This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1. Built on three core principles -- diversity, deliberative reasoning, and rigorous filtering…

Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, and trajectory agents. A central question is how such a system should route among…

Context-dependent semantic parsing has proven to be an important yet challenging task. To leverage the advances in context-independent semantic parsing, we propose to perform follow-up query analysis, aiming to restate context-dependent…

To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG) leverages lightweight retrievers to efficiently extract information from a given…

Modern robotic systems, deployed across domains from industrial automation to domestic assistance, face a critical challenge: executing tasks with precision and adaptability in dynamic, unpredictable environments. To address this, we…

Assessing performance in Natural Language Processing is becoming increasingly complex. One particular challenge is the potential for evaluation datasets to overlap with training data, either directly or indirectly, which can lead to skewed…

AI coding assistants like GitHub Copilot are rapidly transforming software development, but their safety remains deeply uncertain-especially in high-stakes domains like cybersecurity. Current red-teaming tools often rely on fixed benchmarks…

Model merging is an efficient way of obtaining a multi-task model from several pretrained models without further fine-tuning, and it has gained attention in various domains, including natural language processing (NLP). Despite the…

Red teaming is critical for identifying vulnerabilities and building trust in current LLMs. However, current automated methods for Large Language Models (LLMs) rely on brittle prompt templates or single-turn attacks, failing to capture the…

AI systems have the potential to produce both benefits and harms, but without rigorous and ongoing adversarial evaluation, AI actors will struggle to assess the breadth and magnitude of the AI risk surface. Researchers from the field of…

Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human…

Red-teaming is a common practice for mitigating unsafe behaviors in Large Language Models (LLMs), which involves thoroughly assessing LLMs to identify potential flaws and addressing them with responsible and accurate responses. While…

The i* modeling language was introduced to fill the gap in the spectrum of conceptual modeling languages, focusing on the intentional (why?), social (who?), and strategic (how? how else?) dimensions. i* has been applied in many areas, e.g.,…

Deploying large language models (LMs) can pose hazards from harmful outputs such as toxic or false text. Prior work has introduced automated tools that elicit harmful outputs to identify these risks. While this is a valuable step toward…