English
Related papers

Related papers: Likelihood hacking in probabilistic program synthe…

200 papers

In this paper, we consider the problem of learning safe policies for probabilistic-constrained reinforcement learning (RL). Specifically, a safe policy or controller is one that, with high probability, maintains the trajectory of the agent…

Machine Learning · Computer Science 2024-03-14 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

Recent advances in instruction-following large language models (LLMs) have led to dramatic improvements in a range of NLP tasks. Unfortunately, we find that the same improved capabilities amplify the dual-use risks for malicious purposes of…

Cryptography and Security · Computer Science 2023-02-14 Daniel Kang , Xuechen Li , Ion Stoica , Carlos Guestrin , Matei Zaharia , Tatsunori Hashimoto

Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior research has focused on unintended vulnerabilities, this study…

Software Engineering · Computer Science 2025-07-24 Emir Bosnak , Sahand Moslemi , Mayasah Lami , Anil Koyuncu

Large Language Models (LLMs) have become an essential tool in the programmer's toolkit, but their tendency to hallucinate code can be used by malicious actors to introduce vulnerabilities to broad swathes of the software supply chain. In…

Machine Learning · Computer Science 2025-02-03 Arjun Krishna , Erick Galinkin , Leon Derczynski , Jeffrey Martin

With the recent advancement of Large Language Models (LLMs), generating functionally correct code has become less complicated for a wide array of developers. While using LLMs has sped up the functional development process, it poses a heavy…

Cryptography and Security · Computer Science 2024-02-01 Nafis Tanveer Islam , Mohammad Bahrami Karkevandi , Peyman Najafirad

Conditional language models are predominantly trained with maximum likelihood estimation (MLE), giving probability mass to sparsely observed target sequences. While MLE trained models assign high probability to plausible sequences given the…

Computation and Language · Computer Science 2022-10-04 Yao Zhao , Misha Khalman , Rishabh Joshi , Shashi Narayan , Mohammad Saleh , Peter J. Liu

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

Software vulnerability detection is generally supported by automated static analysis tools, which have recently been reinforced by deep learning (DL) models. However, despite the superior performance of DL-based approaches over rule-based…

Software Engineering · Computer Science 2024-05-03 Yanjing Yang , Xin Zhou , Runfeng Mao , Jinwei Xu , Lanxin Yang , Yu Zhangm , Haifeng Shen , He Zhang

Probabilistic programming has become a standard practice to model stochastic events and learn about the behavior of nature in different scientific contexts, ranging from Genetics and Ecology to Linguistics and Psychology. However, domain…

Programming Languages · Computer Science 2025-07-10 Guilherme Espada , Alcides Fonseca

An increasingly common practice is to train large language models (LLMs) using synthetic data. Often this synthetic data is produced by the same or similar LLMs as those it is being used to train. This raises the question of whether the…

Computation and Language · Computer Science 2025-03-18 Lingze Zhang , Ellie Pavlick

Improving and understanding the training dynamics and reasoning of Large Language Models (LLMs) has become essential for their deployment in AI-based security tools, such as software vulnerability detection. In this work, we present an…

Cryptography and Security · Computer Science 2025-07-08 Marco Simoni , Aleksandar Fontana , Giulio Rossolini , Andrea Saracino

Reinforcement learning (RL) has achieved phenomenal success in various domains. However, its data-driven nature also introduces new vulnerabilities that can be exploited by malicious opponents. Recent work shows that a well-trained RL agent…

Machine Learning · Computer Science 2024-03-08 Xiaolin Sun , Zizhan Zheng

In order to reliably process natural language, NLP systems must generalize to the long tail of rare utterances. We propose a method to create challenging benchmarks that require generalizing to the tail of the distribution by re-splitting…

Computation and Language · Computer Science 2023-05-03 Ameya Godbole , Robin Jia

The rapid advancement of Large Language Models (LLMs) has enhanced software development processes, minimizing the time and effort required for coding and enhancing developer productivity. However, despite their potential benefits, code…

Cryptography and Security · Computer Science 2025-04-30 Swaroop Dora , Deven Lunkad , Naziya Aslam , S. Venkatesan , Sandeep Kumar Shukla

Large Language Models (LLMs) can generate code from natural language, but their performance is highly sensitive to prompt formulation. We propose a reinforcement-learning-based framework that models prompt refinement as a sequential…

Software Engineering · Computer Science 2026-05-20 Ali Mohammadi Esfahani , Nafiseh Kahani , Samuel A. Ajila

Large Language Models (LLMs) are gaining momentum in software development with prompt-driven programming enabling developers to create code from natural language (NL) instructions. However, studies have questioned their ability to produce…

Software Engineering · Computer Science 2025-02-27 Catherine Tony , Nicolás E. Díaz Ferreyra , Markus Mutas , Salem Dhiff , Riccardo Scandariato

Large Language Models (LLMs) are increasingly deployed across diverse domains, raising the need for rigorous reliability assessment methods. Existing benchmark-based evaluations primarily offer descriptive statistics of model accuracy over…

Software Engineering · Computer Science 2026-01-30 Robab Aghazadeh-Chakherlou , Qing Guo , Siddartha Khastgir , Peter Popov , Xiaoge Zhang , Xingyu Zhao

Aligning Large Language Models (LLMs) to human preferences in content, style, and presentation is challenging, in part because preferences are varied, context-dependent, and sometimes inherently ambiguous. While successful, Reinforcement…

Machine Learning · Computer Science 2024-10-29 Sam Houliston , Alizée Pace , Alexander Immer , Gunnar Rätsch

Probabilistic programming languages (PPLs) are expressive means for creating and reasoning about probabilistic models. Unfortunately hybrid probabilistic programs, involving both continuous and discrete structures, are not well supported by…

Programming Languages · Computer Science 2024-06-25 Poorva Garg , Steven Holtzen , Guy Van den Broeck , Todd Millstein

Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…