Related papers: R1-ACT: Efficient Reasoning Model Safety Alignment…

Recent years have witnessed significant progress in large language models' (LLMs) reasoning, which is largely due to the chain-of-thought (CoT) approaches, allowing models to generate intermediate reasoning steps before reaching the final…

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…

Recent advances in large reasoning models (LRMs) have enabled remarkable performance on complex tasks such as mathematics and coding by generating long Chain-of-Thought (CoT) traces. In this paper, we identify and systematically analyze a…

Traditional visual grounding methods primarily focus on single-image scenarios with simple textual references. However, extending these methods to real-world scenarios that involve implicit and complex instructions, particularly in…

As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We study this problem by introducing MIR-SafetyBench, the first…

Recent advances in test-time scaling have enabled Large Language Models (LLMs) to display sophisticated reasoning abilities via extended Chain-of-Thought (CoT) generation. Despite their potential, these Reasoning LLMs (RLMs) often…

Ensuring robust safety measures across a wide range of scenarios is crucial for user-facing systems. While Large Language Models (LLMs) can generate valuable data for safety measures, they often exhibit distributional biases, focusing on…

In this paper, we introduce Rank-R1, a novel LLM-based reranker that performs reasoning over both the user query and candidate documents before performing the ranking task. Existing document reranking methods based on large language models…

The rapid emergence of diverse large language models (LLMs) has spurred the development of LLM routers that assign user queries to the most suitable model. However, existing LLM routers typically perform a single-round, one-to-one mapping…

Vision--Language Models (VLMs) show significant promise for Medical Visual Question Answering (VQA), yet their deployment in clinical settings is hindered by severe vulnerability to adversarial attacks. Standard adversarial training, while…

The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit…

Large language models(LLMs) increasingly match expert performance on licensing examinations, yet routine clinical use remains limited because governance requires auditable reasoning, safety and ethics alignment, and resilience to…

Retrieval-Augmented Generation (RAG) systems commonly suffer from Knowledge Conflicts, where retrieved external knowledge contradicts the inherent, parametric knowledge of large language models (LLMs). It adversely affects performance on…

While reasoning large language models (LLMs) demonstrate remarkable performance across various tasks, they also contain notable security vulnerabilities. Recent research has uncovered a "thinking-stopped" vulnerability in DeepSeek-R1, where…

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Recently, Large Reasoning Models (LRMs) have gradually become a research hotspot due to their outstanding performance in handling complex tasks. Among them, DeepSeek R1 has garnered significant attention for its exceptional performance and…

Large reasoning models (LRMs) achieve remarkable performance via long reasoning chains, but often incur excessive computational overhead due to redundant reasoning, especially on simple tasks. In this work, we systematically quantify the…

Safe reinforcement learning (RL) seeks to mitigate unsafe behaviors that arise from exploration during training by reducing constraint violations while maintaining task performance. Existing approaches typically rely on a single policy to…

Large Multimodal Reasoning Models (LMRMs) are moving into real applications, where they must be both useful and safe. Safety is especially challenging in multimodal settings: images and text can be combined to bypass guardrails, and single…

Large Language Models (LLMs), despite their remarkable capabilities, are prone to generating hallucinated or outdated content due to their static internal knowledge. While Retrieval-Augmented Generation (RAG) integrated with Reinforcement…