English
Related papers

Related papers: Tree-based Dialogue Reinforced Policy Optimization…

200 papers

We present an openly documented methodology for fine-tuning language models to detect temporal attack patterns in multi-agent AI workflows using OpenTelemetry trace analysis. We curate a dataset of 80,851 examples from 18 public…

Artificial Intelligence · Computer Science 2026-01-06 Ron F. Del Rosario

Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcement learning methods do not provide an efficient framework for…

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is…

Computation and Language · Computer Science 2025-12-09 Richard Young

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

Computation and Language · Computer Science 2024-12-18 Weixiong Zheng , Peijian Zeng , Yiwei Li , Hongyan Wu , Nankai Lin , Junhao Chen , Aimin Yang , Yongmei Zhou

The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been trained. Sample efficiency is usually not an issue since cheap…

Computation and Language · Computer Science 2023-03-16 Govardana Sachithanandam Ramachandran , Kazuma Hashimoto , Caiming Xiong

Training a dialogue policy using deep reinforcement learning requires a lot of exploration of the environment. The amount of wasted invalid exploration makes their learning inefficient. In this paper, we find and define an important reason…

Human-Computer Interaction · Computer Science 2023-05-08 Yangyang Zhao , Zhenyu Wang , Mehdi Dastani , Shihan Wang

As large language models (LLMs) become increasingly deployed, understanding the complexity and evolution of jailbreaking strategies is critical for AI safety. We present a mass-scale empirical analysis of jailbreak complexity across over 2…

Computation and Language · Computer Science 2026-05-28 Aldan Creo , Raul Castro Fernandez , Manuel Cebrian

Large Language Models (LLMs) can generate human-like disinformation, yet their ability to personalise such content across languages and demographics remains underexplored. This study presents the first large-scale, multilingual analysis of…

Computation and Language · Computer Science 2025-10-30 João A. Leite , Arnav Arora , Silvia Gargova , João Luz , Gustavo Sampaio , Ian Roberts , Carolina Scarton , Kalina Bontcheva

Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emergence of their properties and encoded knowledge, the risk of…

Computation and Language · Computer Science 2023-08-31 Rishabh Bhardwaj , Soujanya Poria

As large language models(LLMs) become commonplace in practical applications, the security issues of LLMs have attracted societal concerns. Although extensive efforts have been made to safety alignment, LLMs remain vulnerable to jailbreak…

Computation and Language · Computer Science 2024-09-20 Xu Zhang , Dinghao Jing , Xiaojun Wan

As large language models (LLMs) are increasingly deployed as black-box components in real-world applications, red teaming has become essential for identifying potential risks. It tests LLMs with adversarial prompts to uncover…

Machine Learning · Computer Science 2026-03-25 Jiale Ding , Xiang Zheng , Yutao Wu , Cong Wang , Wei-Bin Lee , Ling Pan , Xingjun Ma , Yu-Gang Jiang

Conventionally, generation of natural language for dialogue agents may be viewed as a statistical learning problem: determine the patterns in human-provided data and generate appropriate responses with similar statistical properties.…

Computation and Language · Computer Science 2022-04-19 Siddharth Verma , Justin Fu , Mengjiao Yang , Sergey Levine

Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…

Cryptography and Security · Computer Science 2024-10-08 Yiting Dong , Guobin Shen , Dongcheng Zhao , Xiang He , Yi Zeng

Despite their remarkable capabilities, large language models often struggle with tasks requiring complex reasoning and planning. While existing approaches like Chain-of-Thought prompting and tree search techniques show promise, they are…

Machine Learning · Computer Science 2025-02-12 Yang Li

Large language model (LLM) based search agents iteratively generate queries, retrieve external information, and reason to answer open-domain questions. While researchers have primarily focused on improving their utility, their safety…

Computation and Language · Computer Science 2026-03-24 Qiusi Zhan , Angeline Budiman-Chan , Abdelrahman Zayed , Xingzhi Guo , Daniel Kang , Joo-Kyung Kim

The security of cloud environments, such as Amazon Web Services (AWS), is complex and dynamic. Static security policies have become inadequate as threats evolve and cloud resources exhibit elasticity [1]. This paper addresses the…

Cryptography and Security · Computer Science 2025-05-15 Muhammad Saqib , Dipkumar Mehta , Fnu Yashu , Shubham Malhotra

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs.…

Artificial Intelligence · Computer Science 2026-05-29 Jianshuo Dong , Sheng Guo , Hao Wang , Xun Chen , Zhuotao Liu , Tianwei Zhang , Ke Xu , Minlie Huang , Han Qiu

Large language models (LLMs), optimized through human feedback, have rapidly emerged as a leading paradigm for developing intelligent conversational assistants. However, despite their strong performance across many benchmarks, LLM-based…

Computation and Language · Computer Science 2025-07-29 Maximillian Chen , Ruoxi Sun , Tomas Pfister , Sercan Ö. Arık

Eliciting harmful behavior from large language models (LLMs) is an important task to ensure the proper alignment and safety of the models. Often when training LLMs, ethical guidelines are followed yet alignment failures may still be…

Cryptography and Security · Computer Science 2024-08-20 Robert J. Moss

Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as…

Cryptography and Security · Computer Science 2024-10-01 Zeguan Xiao , Yan Yang , Guanhua Chen , Yun Chen
‹ Prev 1 3 4 5 6 7 10 Next ›