Related papers: Adaptive Instruction Composition for Automated LLM…

Large Language Models (LLMs) have exhibited significant potential in performing diverse tasks, including the ability to call functions or use external tools to enhance their performance. While current research on function calling by LLMs…

As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Existing red-teaming efforts are either restricted to a narrow…

Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet they often rely on external context to handle complex tasks. While retrieval-augmented frameworks traditionally focus on selecting top-ranked…

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying the study of adversarial robustness in text scoring models…

Multi-AI collaboration, such as ensembling or debating large language models (LLMs), is a promising paradigm for aggregating information and boosting performance. A foundational step in these pipelines is to feed the responses of several…

Language Model Agents (LMAs) are emerging as a powerful primitive for augmenting red-team operations. They can support attack planning, adversary emulation, and the orchestration of multi-step activity such as lateral movement, a core…

Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting…

With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, which lack adaptability to new data and may…

Many machine learning applications involve jointly predicting multiple mutually dependent output variables. Learning to search is a family of methods where the complex decision problem is cast into a sequence of decisions via a search…

Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial ``jailbreak'' attacks designed to bypass safety guardrails. Current safety alignment methods depend heavily on static external red…

In multi-agent reinforcement learning, decentralized execution is a common approach, yet it suffers from the redundant computation problem. This occurs when multiple agents redundantly perform the same or similar computation due to…

As Large Language Models (LLMs) are widely applied in various domains, the safety of LLMs is increasingly attracting attention to avoid their powerful capabilities being misused. Existing jailbreak methods create a forced…

Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations. Despite progress, theoretical understanding of this phenomenon remains limited. We argue that in-context learning relies on…

Fine-tuning large language models (LLMs) using diverse datasets is crucial for enhancing their overall performance across various domains. In practical scenarios, existing methods based on modeling the mixture proportions of data…

Reasoning methods that adaptively allocate test-time compute have advanced LLM performance on easy to verify domains such as math and code. In this work, we study how to utilize this approach to train models that exhibit a degree of…

Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling…

Human cognition exhibits systematic compositionality, the algebraic ability to generate infinite novel combinations from finite learned components, which is the key to understanding and reasoning about complex logic. In this work, we…

Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space. In other words, these methods mainly search for better…

Drug-drug interaction event (DDIE) prediction is crucial for preventing adverse reactions and ensuring optimal therapeutic outcomes. However, existing methods often face challenges with imbalanced datasets, complex interaction mechanisms,…