Related papers: Self-ReSET: Learning to Self-Recover from Unsafe R…

We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning trajectories as pseudo-gradient descent updates to the LLM's…

LLMs have fundamentally transformed dense retrieval, upgrading backbones from discriminative encoders to generative architectures. However, a critical disconnect remains: while LLMs possess strong reasoning capabilities, current retrievers…

Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to…

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thought. Through…

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely…

Efficiently acquiring external knowledge and up-to-date information is essential for effective reasoning and text generation in large language models (LLMs). Prompting advanced LLMs with reasoning capabilities to use search engines during…

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. However, these systems are vulnerable to adversarial poisoning…

Recent research studies revealed that neural networks are vulnerable to adversarial attacks. State-of-the-art defensive techniques add various adversarial examples in training to improve models' adversarial robustness. However, these…

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Small language models (SLMs) enable low-cost, private, on-device inference, but they often fail on problems that require specialized domain knowledge or multi-step reasoning. Existing approaches for improving reasoning either rely on scale…

Reinforcement learning (RL) has demonstrated potential in enhancing the reasoning capabilities of large language models (LLMs), but such training typically demands substantial efforts in creating and annotating data. In this work, we…

The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought (CoT) is manipulated…

Recent successes of reinforcement learning (RL) in training large reasoning models motivate the question of whether self-training - the process where a model learns from its own judgments - can be sustained within RL. In this work, we study…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Self-driving vehicles must be able to act intelligently in diverse and difficult environments, marked by high-dimensional state spaces, a myriad of optimization objectives and complex behaviors. Traditionally, classical optimization and…

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…