Related papers: STAR: SocioTechnical Approach to Red Teaming Langu…

Stance detection is the view towards a specific target by a given context (\textit{e.g.} tweets, commercial reviews). Target-related knowledge is often needed to assist stance detection models in understanding the target well and making…

The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically evaluating robustness against adversarial behaviors. Existing red-teaming practices are largely manual…

While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given ill-posed or ambiguous queries. We introduce statistically…

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel…

WARNING: This paper contains examples of offensive materials. To address the proliferation of toxic content on social media, we introduce SMARTER, we introduce SMARTER, a data-efficient two-stage framework for explainable content moderation…

In this paper we present STAR-RT - the first working prototype of Selective Tuning Attention Reference (STAR) model and Cognitive Programs (CPs). The Selective Tuning (ST) model received substantial support through psychological and…

Most language models currently available are prone to self-contradiction during dialogues. To mitigate this issue, this study explores a novel contradictory dialogue processing task that aims to detect and modify contradictory statements in…

How should one judge whether a given large language model (LLM) can reliably perform economic reasoning? Most existing LLM benchmarks focus on specific applications and fail to present the model with a rich variety of economic tasks. A…

Experiment commentary is crucial in describing the experimental procedures, delving into underlying scientific principles, and incorporating content-related safety guidelines. In practice, human teachers rely heavily on subject-specific…

The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to…

Understanding and reasoning with abstractive information from the visual modality presents significant challenges for current multi-modal large language models (MLLMs). Among the various forms of abstractive information, Multi-Modal…

LLM-based root cause analysis (RCA) agents have recently emerged as a promising paradigm for incident diagnosis in microservice AIOps. However, their reliability remains fragile: an error in early evidence collection, hypothesis…

Training AI models in cybersecurity with help of vast datasets offers significant opportunities to mimic real-world behaviors effectively. However, challenges like data drift and scarcity of labelled data lead to frequent updates of models…

As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and…

Complex sensors such as LiDAR, RADAR, and event cameras have proliferated in autonomous robotics to enhance perception and understanding of the environment. Meanwhile, these sensors are also vulnerable to diverse failure mechanisms that can…

A lot of effort in recent years have been expended to explain machine learning systems. However, some machine learning methods are inherently explainable, and thus are not completely black box. This enables the developers to make sense of…

As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs, and information provided by other actors. When these inputs can be strategically shaped by…

Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effective and diverse attacks in red-teaming is important, but achieving both is challenging.…

Automated red-teaming has emerged as a scalable approach for auditing Large Language Models (LLMs) prior to deployment, yet existing approaches lack mechanisms to efficiently adapt to model-specific vulnerabilities at inference. We…