English
Related papers

Related papers: STAIR: Improving Safety Alignment with Introspecti…

200 papers

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…

Machine Learning · Computer Science 2025-05-01 Yi Zhou , Wenpeng Xing , Dezhang Kong , Changting Lin , Meng Han

Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) by generating natural language (NL) rationales that lead to the final answer. However, it struggles with numerical…

Artificial Intelligence · Computer Science 2025-02-13 Cheryl Li , Tianyuan Xu , Yiwen Guo

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…

Machine Learning · Computer Science 2026-02-10 Kaustubh Ponkshe , Shaan Shah , Raghav Singhal , Praneeth Vepakomma

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

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…

Computation and Language · Computer Science 2023-09-06 Peiyi Wang , Lei Li , Liang Chen , Feifan Song , Binghuai Lin , Yunbo Cao , Tianyu Liu , Zhifang Sui

Generating step-by-step "chain-of-thought" rationales has proven effective for improving the performance of large language models on complex reasoning tasks. However, applying such techniques to structured tasks, such as text-to-SQL,…

Computation and Language · Computer Science 2025-02-20 Mingqian He , Yongliang Shen , Wenqi Zhang , Qiuying Peng , Jun Wang , Weiming Lu

Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety…

Computation and Language · Computer Science 2024-10-18 Leon Zhou , Junfeng Yang , Chengzhi Mao

Large Language Models (LLMs) exhibit impressive performance across diverse domains but often suffer from overconfidence, limiting their reliability in critical applications. We propose SteerConf, a novel framework that systematically steers…

Computation and Language · Computer Science 2025-05-27 Ziang Zhou , Tianyuan Jin , Jieming Shi , Qing Li

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 reasoning models (LRMs) grow more capable, chain-of-thought (CoT) reasoning introduces new safety challenges. Existing SFT-based safety alignment studies dominantly focused on filtering prompts with safe, high-quality responses,…

Computation and Language · Computer Science 2026-03-31 Raj Vardhan Tomar , Preslav Nakov , Yuxia Wang

Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into…

Cryptography and Security · Computer Science 2026-02-17 Shang Liu , Hanyu Pei , Zeyan Liu

Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to…

Machine Learning · Computer Science 2024-02-28 Heegyu Kim , Sehyun Yuk , Hyunsouk Cho

The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable…

Computation and Language · Computer Science 2024-11-06 Zhexin Zhang , Yida Lu , Jingyuan Ma , Di Zhang , Rui Li , Pei Ke , Hao Sun , Lei Sha , Zhifang Sui , Hongning Wang , Minlie Huang

Large Language Models (LLMs) have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research. However, they remain vulnerable to jailbreak attacks, which manipulate the…

Cryptography and Security · Computer Science 2026-01-05 Haoran Gu , Handing Wang , Yi Mei , Mengjie Zhang , Yaochu Jin

Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to improve their internal reasoning ability by integrating external tools. However, models employing TIR often display suboptimal behaviors, such as insufficient or…

Artificial Intelligence · Computer Science 2025-10-01 Yifei Chen , Guanting Dong , Zhicheng Dou

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Computation and Language · Computer Science 2025-03-03 Samuele Poppi , Zheng-Xin Yong , Yifei He , Bobbie Chern , Han Zhao , Aobo Yang , Jianfeng Chi

Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools during reasoning. Existing TIR methods typically rely on external tool documentation during…

Computation and Language · Computer Science 2026-04-14 Qiancheng Xu , Yongqi Li , Fan Liu , Hongru Wang , Min Yang , Wenjie Li

Recent advances in large language models (LLMs) have predominantly focused on maximizing accuracy and reasoning capabilities, often overlooking crucial computational efficiency considerations. While this approach has yielded impressive…

Machine Learning · Computer Science 2024-12-24 Marwan AbdElhameed , Pavly Halim

Emerging large reasoning models (LRMs), such as DeepSeek-R1 models, leverage long chain-of-thought (CoT) reasoning to generate structured intermediate steps, enhancing their reasoning capabilities. However, long CoT does not inherently…

Artificial Intelligence · Computer Science 2025-02-18 Fengqing Jiang , Zhangchen Xu , Yuetai Li , Luyao Niu , Zhen Xiang , Bo Li , Bill Yuchen Lin , Radha Poovendran