English
Related papers

Related papers: Peak + Accumulation: A Proxy-Level Scoring Formula…

200 papers

Recent large language model (LLM) defenses have greatly improved models' ability to refuse harmful queries, even when adversarially attacked. However, LLM defenses are primarily evaluated against automated adversarial attacks in a single…

Machine Learning · Computer Science 2024-09-05 Nathaniel Li , Ziwen Han , Ian Steneker , Willow Primack , Riley Goodside , Hugh Zhang , Zifan Wang , Cristina Menghini , Summer Yue

Large Language Models (LLMs) have been widely deployed across various applications, yet their potential security and ethical risks have raised increasing concerns. Existing research employs red teaming evaluations, utilizing multi-turn…

Cryptography and Security · Computer Science 2025-11-06 Yize Liu , Yunyun Hou , Aina Sui

Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety alignment and elicit harmful responses. A growing body of work shows that contextual priming, where earlier turns covertly bias later replies,…

Computation and Language · Computer Science 2026-05-05 Mario Rodríguez Béjar , Francisco J. Cortés-Delgado , S. Braghin , Jose L. Hernández-Ramos

The increasing deployment of large language models in security-sensitive domains necessitates rigorous evaluation of their resilience against adversarial prompt-based attacks. While previous benchmarks have focused on security evaluations…

Cryptography and Security · Computer Science 2025-09-22 Huining Cui , Wei Liu

Conversational scams, such as romance and investment scams, are emerging as a major form of online fraud. Unlike one-shot scam lures such as fake lottery or unpaid toll messages, they unfold through multi-turn conversations in which…

Computation and Language · Computer Science 2026-05-13 Weixiang Sun , Shang Ma , Yiyang Li , Tianyi Ma , Zehong Wang , Colby Nelson , Xusheng Xiao , Yanfang Ye

Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action. In this…

Cryptography and Security · Computer Science 2025-04-24 Kuo-Han Hung , Ching-Yun Ko , Ambrish Rawat , I-Hsin Chung , Winston H. Hsu , Pin-Yu Chen

Reward hacking arises when a model improves a proxy reward by exploiting shortcuts rather than solving the intended task. We study this failure mode through the geometry of reinforcement learning updates in language models and argue that…

Machine Learning · Computer Science 2026-05-26 Wenlong Deng , Jiaji Huang , Kaan Ozkara , Yushu Li , Christos Thrampoulidis , Xiaoxiao Li , Youngsuk Park

Large Language Models (LLMs) continue to exhibit vulnerabilities to jailbreaking attacks: carefully crafted malicious inputs intended to circumvent safety guardrails and elicit harmful responses. As such, we present AutoAdv, a novel…

Cryptography and Security · Computer Science 2025-12-25 Aashray Reddy , Andrew Zagula , Nicholas Saban

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

Computation and Language · Computer Science 2026-03-23 Zafir Shamsi , Nikhil Chekuru , Zachary Guzman , Shivank Garg

Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances. However, most existing methods rely mainly on models internal parametric knowledge, without explicit…

Computation and Language · Computer Science 2026-04-21 Juhyeon Lee , Wonduk Seo , Junseo Koh , Seunghyun Lee , Haihua Chen , Yi Bu

Large Language Models (LLMs) have transformed task automation and content generation across various domains while incorporating safety filters to prevent misuse. We introduce a novel jailbreaking framework that employs distributed prompt…

Cryptography and Security · Computer Science 2025-04-01 Johan Wahréus , Ahmed Hussain , Panos Papadimitratos

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

Computation and Language · Computer Science 2024-10-22 Yihua Zhou , Xiaochuan Shi

Single-prompt evaluations dominate current LLM benchmarking, yet they fail to capture the conversational dynamics where real-world harm occurs. In this study, we examined whether conversation length affects response veracity by evaluating…

Computation and Language · Computer Science 2026-01-26 Karl Neergaard , Le Qiu , Emmanuele Chersoni

Large language models increasingly rely on either reinforcement learning or multi-agent prompting to improve reasoning, yet these two paradigms remain difficult to combine. Directly applying single-agent reinforcement learning to multi-turn…

Artificial Intelligence · Computer Science 2026-05-28 Chusen Li , Zhou Liu , Shuigeng Zhou , Wentao Zhang

Memory-augmented LLM agents store and retrieve information from prior interactions, yet the relative importance of how memories are written versus how they are retrieved remains unclear. We introduce a diagnostic framework that analyzes how…

Artificial Intelligence · Computer Science 2026-04-14 Boqin Yuan , Yue Su , Kun Yao

We present MultiChallenge, a pioneering benchmark evaluating large language models (LLMs) on conducting multi-turn conversations with human users, a crucial yet underexamined capability for their applications. MultiChallenge identifies four…

Computation and Language · Computer Science 2025-03-07 Ved Sirdeshmukh , Kaustubh Deshpande , Johannes Mols , Lifeng Jin , Ed-Yeremai Cardona , Dean Lee , Jeremy Kritz , Willow Primack , Summer Yue , Chen Xing

As large language models (LLMs) constantly evolve, ensuring their safety remains a critical research problem. Previous red-teaming approaches for LLM safety have primarily focused on single prompt attacks or goal hijacking. To the best of…

Computation and Language · Computer Science 2024-06-26 Erxin Yu , Jing Li , Ming Liao , Siqi Wang , Zuchen Gao , Fei Mi , Lanqing Hong

As the pre-trained language models (PLMs) continue to grow, so do the hardware and data requirements for fine-tuning PLMs. Therefore, the researchers have come up with a lighter method called \textit{Prompt Learning}. However, during the…

Computation and Language · Computer Science 2022-09-07 Yundi Shi , Piji Li , Changchun Yin , Zhaoyang Han , Lu Zhou , Zhe Liu

Large language models (LLMs) provide excellent text-generation capabilities, but standard prompting and generation methods generally do not lead to intentional or goal-directed agents and might necessitate considerable prompt tuning. This…

Computation and Language · Computer Science 2023-12-01 Marwa Abdulhai , Isadora White , Charlie Snell , Charles Sun , Joey Hong , Yuexiang Zhai , Kelvin Xu , Sergey Levine

The performance of Large Language Models (LLMs) in reasoning tasks depends heavily on prompt design, with Chain-of-Thought (CoT) and self-consistency being critical methods that enhance this ability. However, these methods do not fully…

Computation and Language · Computer Science 2024-10-08 Chuanyang Zheng , Zhengying Liu , Enze Xie , Zhenguo Li , Yu Li