English
Related papers

Related papers: Benchmarking Reward Hack Detection in Code Environ…

200 papers

With the proliferation of LLM-integrated applications such as GPT-s, millions are deployed, offering valuable services through proprietary instruction prompts. These systems, however, are prone to prompt extraction attacks through…

Cryptography and Security · Computer Science 2024-10-29 Junlin Wang , Tianyi Yang , Roy Xie , Bhuwan Dhingra

Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying the study of adversarial robustness in text scoring models…

Computation and Language · Computer Science 2026-02-03 Manveer Singh Tamber , Hosna Oyarhoseini , Jimmy Lin

Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor uniformly less trustworthy. Yet hallucination reduction is usually instantiated through one…

Artificial Intelligence · Computer Science 2026-05-19 Tej Sanibh Ranade

Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models with human values, reward hacking, also termed reward overoptimization, remains a critical challenge. This issue primarily arises from…

Machine Learning · Computer Science 2024-11-04 Yuchun Miao , Sen Zhang , Liang Ding , Rong Bao , Lefei Zhang , Dacheng Tao

Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capability of large language models (LLMs) and also benefit downstream tasks such as code…

Machine Learning · Computer Science 2026-05-19 Zhanyue Qin , Jia Feng , Yibo Lyu , Yun Peng , Dianbo Sui , Cuiyun Gao , Qing Liao

We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults, sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt…

Machine Learning · Computer Science 2025-10-07 Taeyoung Yun , Pierre-Luc St-Charles , Jinkyoo Park , Yoshua Bengio , Minsu Kim

Data contamination is a known threat to the reliability of model evaluation. However, it remains underexplored in code large language models (LLMs), where contamination often goes beyond exact duplication. We present TRACER, a…

Software Engineering · Computer Science 2026-05-26 Yifeng Di , Xuliang Huang , Tianyi Zhang

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

Machine Learning · Computer Science 2026-04-30 Disha Singha

The widespread adoption of large language models (LLMs) has raised concerns about their safety and reliability, particularly regarding their vulnerability to adversarial attacks. In this paper, we propose a novel perspective that attributes…

Machine Learning · Computer Science 2025-04-22 Zhihui Xie , Jiahui Gao , Lei Li , Zhenguo Li , Qi Liu , Lingpeng Kong

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to achieve remarkable reasoning in domains like mathematics and coding, where verifiable rewards provide clear signals. However, extending this paradigm to financial…

Artificial Intelligence · Computer Science 2026-01-09 Rui Sun , Yifan Sun , Sheng Xu , Li Zhao , Jing Li , Daxin Jiang , Cheng Hua , Zuo Bai

We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline…

Cryptography and Security · Computer Science 2026-04-21 Ivan Bercovich , Ivgeni Segal , Kexun Zhang , Shashwat Saxena , Aditi Raghunathan , Ziqian Zhong

The use of Large Language Models (LLMs) as automatic judges for code evaluation is becoming increasingly prevalent in academic environments. But their reliability can be compromised by students who may employ adversarial prompting…

Software Engineering · Computer Science 2026-02-04 Devanshu Sahoo , Vasudev Majhi , Arjun Neekhra , Yash Sinha , Murari Mandal , Dhruv Kumar

In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs. A well-formatted, verbose but less helpful response from the LLMs can often…

Machine Learning · Computer Science 2024-02-13 Lichang Chen , Chen Zhu , Davit Soselia , Jiuhai Chen , Tianyi Zhou , Tom Goldstein , Heng Huang , Mohammad Shoeybi , Bryan Catanzaro

Ransomware has become a critical threat to cybersecurity due to its rapid evolution, the necessity for early detection, and growing diversity, posing significant challenges to traditional detection methods. While AI-based approaches had…

Cryptography and Security · Computer Science 2025-10-28 Zhixin Pan , Ziyu Shu , Amberbir Alemayoh

The rapid evolution of cyber threats has highlighted significant gaps in security knowledge integration. Cybersecurity Knowledge Graphs (CKGs) relying on structured data inherently exhibit hysteresis, as the timely incorporation of rapidly…

Cryptography and Security · Computer Science 2026-02-13 Zijing Xu , Ziwei Ning , Tiancheng Hu , Jianwei Zhuge , Yangyang Wang , Jiahao Cao , Mingwei Xu

The emergence of reinforcement learning in post-training of large language models has sparked significant interest in reward models. Reward models assess the quality of sampled model outputs to generate training signals. This task is also…

Computation and Language · Computer Science 2025-10-06 Sebastian Gehrmann

Reinforcement Learning from Verifiable Rewards (RLVR) has recently shown that large language models (LLMs) can develop their own reasoning without direct supervision. However, applications in the medical domain, specifically for question…

Machine Learning · Computer Science 2025-09-22 Mirza Farhan Bin Tarek , Rahmatollah Beheshti

In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects optimizing reasoning quality. Bringing process-level supervision into RL is appealing, but it faces…

Software Engineering · Computer Science 2026-05-06 Lishui Fan , Yu Zhang , Mouxiang Chen , Zhongxin Liu

The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and…

Computation and Language · Computer Science 2024-07-09 Cheng Wang , Xinyang Lu , See-Kiong Ng , Bryan Kian Hsiang Low

Jailbreak attacks aim to bypass the LLMs' safeguards. While researchers have proposed different jailbreak attacks in depth, they have done so in isolation -- either with unaligned settings or comparing a limited range of methods. To fill…

Cryptography and Security · Computer Science 2025-05-27 Junjie Chu , Yugeng Liu , Ziqing Yang , Xinyue Shen , Michael Backes , Yang Zhang