English
Related papers

Related papers: RAPO: Risk-Aware Preference Optimization for Gener…

200 papers

Large Reasoning Models (LRMs) have achieved remarkable success, yet they often suffer from producing unnecessary and verbose reasoning chains. We identify a core aspect of this issue as "invalid thinking" -- models tend to repeatedly…

Artificial Intelligence · Computer Science 2025-09-12 Zhengxiang Cheng , Dongping Chen , Mingyang Fu , Tianyi Zhou

Long Chain-of-Thought (LCoT), achieved by Reinforcement Learning with Verifiable Rewards (RLVR), has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs). However, reasoning in current LLMs is primarily…

Large language models (LLMs) offer unprecedented and growing capabilities, but also introduce complex safety and security challenges that resist conventional risk management. While conventional probabilistic risk analysis (PRA) requires…

Cryptography and Security · Computer Science 2025-05-26 Alexander Gutfraind , Vicki Bier

Large reasoning models (LRMs) have achieved remarkable progress on complex tasks by generating extended chains of thought (CoT). However, their uncontrolled output lengths pose significant challenges for real-world deployment, where…

Machine Learning · Computer Science 2025-05-22 Yuhui Xu , Hanze Dong , Lei Wang , Doyen Sahoo , Junnan Li , Caiming Xiong

Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during…

Artificial Intelligence · Computer Science 2025-04-09 Wenxuan Zhang , Philip H. S. Torr , Mohamed Elhoseiny , Adel Bibi

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

Cryptography and Security · Computer Science 2026-04-03 Nanxi Li , Zhengyue Zhao , G. Edward Suh , Marco Pavone , Chaowei Xiao

Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution shift. Current approaches typically address this issue…

Computation and Language · Computer Science 2025-06-17 Qiyuan Deng , Xuefeng Bai , Kehai Chen , Yaowei Wang , Liqiang Nie , Min Zhang

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…

Cryptography and Security · Computer Science 2026-04-30 Zheng-Xin Yong , Stephen H. Bach

The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift from superficial instruction following to rigorous long-horizon reasoning. While Group Relative Policy Optimization (GRPO) has emerged as a pivotal mechanism for…

Artificial Intelligence · Computer Science 2026-01-01 Xuan Xie , Xuan Wang , Wenjie Wang , Shuai Chen , Wei Lin

Recent advances in large language models (LLMs) have introduced latent reasoning as a promising alternative to autoregressive reasoning. By performing internal computation with hidden states from previous steps, latent reasoning benefit…

Computation and Language · Computer Science 2025-10-24 Zhenrui Yue , Bowen Jin , Huimin Zeng , Honglei Zhuang , Zhen Qin , Jinsung Yoon , Lanyu Shang , Jiawei Han , Dong Wang

Recent advances in large language models (LLMs) have shown strong reasoning capabilities through large-scale pretraining and post-training reinforcement learning, demonstrated by DeepSeek-R1. However, current post-training methods, such as…

Artificial Intelligence · Computer Science 2025-12-04 Boyang Gu , Hongjian Zhou , Bradley Max Segal , Jinge Wu , Zeyu Cao , Hantao Zhong , Lei Clifton , Fenglin Liu , David A. Clifton

Large reasoning models (LRMs) like OpenAI o1 and DeepSeek R1 have demonstrated impressive performance on complex reasoning tasks like mathematics and programming with long Chain-of-Thought (CoT) reasoning sequences (slow-thinking), compared…

Artificial Intelligence · Computer Science 2025-07-15 Jason Zhu , Hongyu Li

Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content.…

Computation and Language · Computer Science 2024-06-13 Bochuan Cao , Yuanpu Cao , Lu Lin , Jinghui Chen

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks, sparking growing interest in their application to preference reasoning in recommendation systems. Existing methods typically…

Artificial Intelligence · Computer Science 2025-10-27 Yang Zhang , Wenxin Xu , Xiaoyan Zhao , Wenjie Wang , Fuli Feng , Xiangnan He , Tat-Seng Chua

Large language models (LLMs) benefit substantially from supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) in reasoning tasks. However, these recipes perform poorly in instruction-based molecular…

Machine Learning · Computer Science 2026-03-09 Xuan Li , Zhanke Zhou , Zongze Li , Jiangchao Yao , Yu Rong , Lu Zhang , Bo Han

Large Language Models (LLMs) have achieved remarkable success across diverse tasks, largely driven by well-designed prompts. However, crafting and selecting such prompts often requires considerable human effort, significantly limiting its…

Computation and Language · Computer Science 2025-03-20 Dengyun Peng , Yuhang Zhou , Qiguang Chen , Jinhao Liu , Jingjing Chen , Libo Qin

Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to…

Computation and Language · Computer Science 2024-07-08 Yuyan Chen , Zhihao Wen , Ge Fan , Zhengyu Chen , Wei Wu , Dayiheng Liu , Zhixu Li , Bang Liu , Yanghua Xiao

Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series,…

Computation and Language · Computer Science 2026-04-02 Mingjie Li , Wai Man Si , Michael Backes , Yang Zhang , Yisen Wang

As large language models (LLMs) continue to advance in capabilities, ensuring their safety against jailbreak attacks remains a critical challenge. In this paper, we introduce a novel safety alignment approach called Answer-Then-Check, which…

Machine Learning · Computer Science 2026-03-09 Chentao Cao , Xiaojun Xu , Bo Han , Hang Li

Safety alignment is an important procedure before the official deployment of a Large Language Model (LLM). While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs)…

Cryptography and Security · Computer Science 2025-06-06 Tiansheng Huang , Sihao Hu , Fatih Ilhan , Selim Furkan Tekin , Zachary Yahn , Yichang Xu , Ling Liu