English
Related papers

Related papers: BAIT: Boundary-Guided Disclosure Escalation via Se…

200 papers

Large language models have consistently struggled with complex reasoning tasks, such as mathematical problem-solving. Investigating the internal reasoning mechanisms of these models can help us design better model architectures and training…

Artificial Intelligence · Computer Science 2025-09-10 Zhiwei Wang , Yunji Wang , Zhongwang Zhang , Zhangchen Zhou , Hui Jin , Tianyang Hu , Jiacheng Sun , Zhenguo Li , Yaoyu Zhang , Zhi-Qin John Xu

Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect with standard heuristics. A particularly challenging failure mode occurs when an attacker tries…

Artificial Intelligence · Computer Science 2026-02-24 Amirhossein Farzam , Majid Behabahani , Mani Malek , Yuriy Nevmyvaka , Guillermo Sapiro

Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by decomposing complex problems into step-by-step solutions, improving performance on reasoning tasks. However, current CoT disclosure policies vary widely across…

Computers and Society · Computer Science 2025-03-20 Yihang Chen , Haikang Deng , Kaiqiao Han , Qingyue Zhao

Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned models. We show that we can monitor a frontier reasoning…

Artificial Intelligence · Computer Science 2025-03-18 Bowen Baker , Joost Huizinga , Leo Gao , Zehao Dou , Melody Y. Guan , Aleksander Madry , Wojciech Zaremba , Jakub Pachocki , David Farhi

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

Computation and Language · Computer Science 2025-11-26 Isack Lee , Haebin Seong

Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior may be explicit, i.e. verbalized in the model's…

Artificial Intelligence · Computer Science 2026-03-03 Xinpeng Wang , Nitish Joshi , Barbara Plank , Rico Angell , He He

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…

Cryptography and Security · Computer Science 2025-09-05 Chuhan Zhang , Ye Zhang , Bowen Shi , Yuyou Gan , Tianyu Du , Shouling Ji , Dazhan Deng , Yingcai Wu

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

While modern LLMs are aligned to refuse harmful requests, it is essential to understand the underlying mechanistic basis of this refusal behavior for model safety analysis. For example, steering-based jailbreak attacks exploit this by…

Artificial Intelligence · Computer Science 2026-05-28 Su-Hyeon Kim , Hyundong Jin , Yejin Lee , Yo-Sub Han

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Cryptography and Security · Computer Science 2024-12-03 Erick Galinkin , Martin Sablotny

In experimental applications of bounded-reasoning models, behavior is often summarized by distributions of "levels". We argue that such summaries conflate two conceptually distinct dimensions: a player's type, capturing beliefs about what…

Theoretical Economics · Economics 2026-04-15 Shuige Liu , Gabriel Ziegler

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire…

Cryptography and Security · Computer Science 2024-11-13 Xirui Li , Ruochen Wang , Minhao Cheng , Tianyi Zhou , Cho-Jui Hsieh

Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or…

Cryptography and Security · Computer Science 2025-05-21 Tiehan Cui , Yanxu Mao , Peipei Liu , Congying Liu , Datao You

Recently, self-learning methods based on user satisfaction metrics and contextual bandits have shown promising results to enable consistent improvements in conversational AI systems. However, directly targeting such metrics by off-policy…

Machine Learning · Computer Science 2023-05-16 Mohammad Kachuee , Sungjin Lee

Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reasoning should lead to more robust safety behavior, we find evidence to the contrary:…

Artificial Intelligence · Computer Science 2026-05-26 Jianli Zhao , Tingchen Fu , Rylan Schaeffer , Mrinank Sharma , Fazl Barez

Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…

Computation and Language · Computer Science 2025-10-28 Havva Alizadeh Noughabi , Julien Serbanescu , Fattane Zarrinkalam , Ali Dehghantanha

As LLMs gain stronger reasoning capabilities, their extended chain-of-thought introduces new degrees of complexity for defending against adversarial jailbreaks and prompt injection. We study consistency training, a family of fine-tuning…

Machine Learning · Computer Science 2026-05-28 Avidan Shah , Jannik Brinkmann , Rico Angell

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly…

Cryptography and Security · Computer Science 2025-06-10 Yukai Zhou , Sibei Yang , Wenjie Wang

Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…

Computation and Language · Computer Science 2026-03-17 Yu Liu , Wenxiao Zhang , Diandian Guo , Cong Cao , Fangfang Yuan , Qiang Sun , Yanbing Liu , Jin B. Hong , Zhiyuan Ma

Recent progress in reinforcement learning with verifiable rewards (RLVR) offers a practical path to self-improvement of language models, but existing methods face a key trade-off: endogenous self-play can drift over iterations, while…

Machine Learning · Computer Science 2026-03-25 Fangyuan Li , Pengfei Li , Shijie Wang , Junqi Gao , Jianxing Liu , Biqing Qi , Yuqiang Li
‹ Prev 1 4 5 6 7 8 10 Next ›