Related papers: SIRAJ: Diverse and Efficient Red-Teaming for LLM A…

Advances in large language models (LLMs) significantly enhance reasoning capabilities but their deployment is restricted in resource-constrained scenarios. Knowledge distillation addresses this by transferring knowledge from powerful…

Most multi-agent systems rely exclusively on autoregressive language models (ARMs) that are based on sequential generation. Although effective for fluent text, ARMs limit global reasoning and plan revision. On the other hand, Discrete…

Task-oriented LLM-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules. The challenge lies in ensuring that the agent consistently adheres to these rules and policies,…

Single-step retrieval-augmented generation (RAG) provides an efficient way to incorporate external information for simple question answering tasks but struggles with complex questions. Agentic RAG extends this paradigm by replacing…

Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters, enabling dynamic execution, debugging, and interactive programming capabilities. While these advancements…

Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…

Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly in privacy-sensitive and resource-constrained environments. Moreover, since vulnerable…

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

With the deployment of Large Language Models (LLMs) in interactive applications, online malicious intent detection has become increasingly critical. However, existing approaches fall short of handling diverse and complex user queries in…

The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). At test time, collaborative reasoning through Multi-Agent Debate (MAD) has emerged as a…

Reasoning segmentation enables open-set object segmentation via implicit text queries, therefore serving as a foundation for embodied agents that should operate autonomously in real-world environments. However, existing methods for…

Pretrained foundation models have exhibited extraordinary in-context learning performance, allowing zero-shot generalization to new tasks not encountered during pretraining. In the case of reinforcement learning (RL), in-context RL (ICRL)…

As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various…

We present a novel framework that bridges the gap between the interpretability of decision trees and the advanced reasoning capabilities of large language models (LLMs) to predict startup success. Our approach leverages chain-of-thought…

Large Language Models (LLMs) have shown potential in automatic bundle generation but suffer from prohibitive computational costs. Although knowledge distillation offers a pathway to more efficient student models, our preliminary study…

Large Language Models (LLMs), especially their compact efficiency-oriented variants, remain susceptible to jailbreak attacks that can elicit harmful outputs despite extensive alignment efforts. Existing adversarial prompt generation…

Red teaming is a common strategy for identifying weaknesses in generative language models (LMs), where adversarial prompts are produced that trigger an LM to generate unsafe responses. Red teaming is instrumental for both model alignment…

Multi-agent systems (MAS) powered by large language models (LLMs) hold significant promise for solving complex decision-making tasks. However, the core process of collaborative decision-making (CDM) within these systems remains…

Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies…

Large Language Models (LLMs) excel at understanding the semantic relationships between queries and documents, even with lengthy and complex long-tail queries. These queries are challenging for feedback-based rankings due to sparse user…