English
Related papers

Related papers: MetaSC: Test-Time Safety Specification Optimizatio…

200 papers

Recent developments in large language models (LLMs) have been impressive. However, these models sometimes show inconsistencies and problematic behavior, such as hallucinating facts, generating flawed code, or creating offensive and toxic…

Computation and Language · Computer Science 2024-02-22 Zhibin Gou , Zhihong Shao , Yeyun Gong , Yelong Shen , Yujiu Yang , Nan Duan , Weizhu Chen

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by…

Computation and Language · Computer Science 2024-01-25 Lingfeng Shen , Weiting Tan , Sihao Chen , Yunmo Chen , Jingyu Zhang , Haoran Xu , Boyuan Zheng , Philipp Koehn , Daniel Khashabi

The last two years have seen a rapid growth in concerns around the safety of large language models (LLMs). Researchers and practitioners have met these concerns by creating an abundance of datasets for evaluating and improving LLM safety.…

Computation and Language · Computer Science 2025-01-13 Paul Röttger , Fabio Pernisi , Bertie Vidgen , Dirk Hovy

Despite efforts to align large language models (LLMs) with societal and moral values, these models remain susceptible to jailbreak attacks -- methods designed to elicit harmful responses. Jailbreaking black-box LLMs is considered…

Computation and Language · Computer Science 2025-09-23 Muyang Zheng , Yuanzhi Yao , Changting Lin , Caihong Kai , Yanxiang Chen , Zhiquan Liu

The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak…

Computation and Language · Computer Science 2024-03-25 Zezhong Wang , Fangkai Yang , Lu Wang , Pu Zhao , Hongru Wang , Liang Chen , Qingwei Lin , Kam-Fai Wong

Large language models (LLMs) are designed to align with human values in their responses. This study exploits LLMs with an iterative prompting technique where each prompt is systematically modified and refined across multiple iterations to…

Computation and Language · Computer Science 2025-03-27 Shih-Wen Ke , Guan-Yu Lai , Guo-Lin Fang , Hsi-Yuan Kao

Large language models (LLMs) have achieved widespread adoption across numerous applications. However, many LLMs are vulnerable to malicious attacks even after safety alignment. These attacks typically bypass LLMs' safety guardrails by…

Cryptography and Security · Computer Science 2025-06-17 Yucheng Li , Surin Ahn , Huiqiang Jiang , Amir H. Abdi , Yuqing Yang , Lili Qiu

Safety alignment in large language models (LLMs) is commonly implemented as a single static policy embedded in model parameters. However, real-world deployments often require context-dependent safety rules that vary across users, regions,…

Artificial Intelligence · Computer Science 2026-03-18 Jingyu Peng , Hongyu Chen , Jiancheng Dong , Maolin Wang , Wenxi Li , Yuchen Li , Kai Zhang , Xiangyu Zhao

Converting high-level tasks described by natural language into formal specifications like Linear Temporal Logic (LTL) is a key step towards providing formal safety guarantees over cyber-physical systems (CPS). While the compliance of the…

Logic in Computer Science · Computer Science 2026-04-28 Junle Li , Siqi Chen , Jiakai Li , Meiqi Tian , Bingzhuo Zhong

The use of domain-specific modeling for development of complex (cyber-physical) systems is gaining increasing acceptance in the industrial environment. Domain-specific modeling allows complex systems and data to be abstracted for a more…

Software Engineering · Computer Science 2021-11-09 Vanessa Tietz

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash…

Computation and Language · Computer Science 2025-06-12 Bang An , Sicheng Zhu , Ruiyi Zhang , Michael-Andrei Panaitescu-Liess , Yuancheng Xu , Furong Huang

Critique, as a natural language description for assessing the quality of model-generated content, has played a vital role in the training, evaluation, and refinement of LLMs. However, a systematic method to evaluate the quality of critique…

Computation and Language · Computer Science 2024-06-04 Shichao Sun , Junlong Li , Weizhe Yuan , Ruifeng Yuan , Wenjie Li , Pengfei Liu

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…

Computation and Language · Computer Science 2025-01-31 Sunbowen Lee , Shiwen Ni , Chi Wei , Shuaimin Li , Liyang Fan , Ahmadreza Argha , Hamid Alinejad-Rokny , Ruifeng Xu , Yicheng Gong , Min Yang

Increasing test-time computation has emerged as a promising direction for improving language model performance, particularly in scenarios where model finetuning is impractical or impossible due to computational constraints or private model…

Computation and Language · Computer Science 2025-12-22 Gonçalo Faria , Noah A. Smith

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Machine Learning · Computer Science 2025-06-06 Shaona Ghosh , Amrita Bhattacharjee , Yftah Ziser , Christopher Parisien

Recent research on large language model (LLM) jailbreaks has primarily focused on techniques that bypass safety mechanisms to elicit overtly harmful outputs. However, such efforts often overlook attacks that exploit the model's capacity for…

Computation and Language · Computer Science 2025-12-01 Zhaoxin Zhang , Borui Chen , Yiming Hu , Youyang Qu , Tianqing Zhu , Longxiang Gao

This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…

Cryptography and Security · Computer Science 2026-05-04 Md. Mehedi Hasan , Sk Tanzir Mehedi , Ziaur Rahman , Rafid Mostafiz , Md. Abir Hossain

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

Cryptography and Security · Computer Science 2025-11-13 Daniyal Ganiuly , Assel Smaiyl

Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or running RL with 0/1 outcome reward, but do these approaches…

In this paper, we tackle the emerging challenge of unintended harmful content generation in Large Language Models (LLMs) with a novel dual-stage optimisation technique using adversarial fine-tuning. Our two-pronged approach employs an…

Computation and Language · Computer Science 2023-08-29 Charles O'Neill , Jack Miller , Ioana Ciuca , Yuan-Sen Ting , Thang Bui
‹ Prev 1 4 5 6 7 8 10 Next ›