English
Related papers

Related papers: Large Language Models Sometimes Generate Purely Ne…

200 papers

Large language models are shown to memorize privacy information such as social security numbers in training data. Given the sheer scale of the training corpus, it is challenging to screen and filter these privacy data, either manually or…

Computation and Language · Computer Science 2022-06-27 Xuandong Zhao , Lei Li , Yu-Xiang Wang

Large Language Models' knowledge of how to perform cyber-security attacks, create bioweapons, and manipulate humans poses risks of misuse. Previous work has proposed methods to unlearn this knowledge. Historically, it has been unclear…

Machine Learning · Computer Science 2025-02-10 Aghyad Deeb , Fabien Roger

Large language models (LLMs), trained on large-scale text, have recently attracted significant attention for their strong performance across many tasks. Motivated by this, we investigate whether a text-trained LLM can help localize fake…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-13 Lin Zhang , Thomas Thebaud , Zexin Cai , Sanjeev Khudanpur , Daniel Povey , Leibny Paola García-Perera , Matthew Wiesner , Nicholas Andrews

How do large language models (LLMs) develop and evolve over the course of training? How do these patterns change as models scale? To answer these questions, we introduce \textit{Pythia}, a suite of 16 LLMs all trained on public data seen in…

Why do language models trained on contradictory data prefer correct answers? In controlled experiments with small transformers (3.5M--86M parameters), we show that this preference tracks the compressibility structure of errors rather than…

Computation and Language · Computer Science 2026-04-07 Konstantin Krestnikov

Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidence in factual claims or cover up evidence of covert actions. Such dishonesty may arise due to the…

Machine Learning · Computer Science 2025-12-24 Manas Joglekar , Jeremy Chen , Gabriel Wu , Jason Yosinski , Jasmine Wang , Boaz Barak , Amelia Glaese

In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…

In programming by example, users "write" programs by generating a small number of input-output examples and asking the computer to synthesize consistent programs. We consider a challenging problem in this domain: learning regular…

Artificial Intelligence · Computer Science 2018-09-28 Long Ouyang

This paper revisits the robust overfitting phenomenon of adversarial training. Observing that models with better robust generalization performance are less certain in predicting adversarially generated training inputs, we argue that…

Machine Learning · Computer Science 2025-01-15 Minxing Zhang , Michael Backes , Xiao Zhang

Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are…

Computation and Language · Computer Science 2023-10-31 Zeqiu Wu , Yushi Hu , Weijia Shi , Nouha Dziri , Alane Suhr , Prithviraj Ammanabrolu , Noah A. Smith , Mari Ostendorf , Hannaneh Hajishirzi

Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing…

Machine Learning · Computer Science 2023-03-07 Nicholas Carlini , Daphne Ippolito , Matthew Jagielski , Katherine Lee , Florian Tramer , Chiyuan Zhang

A novel hack involving Large Language Models (LLMs) has emerged, exploiting adversarial suffixes to deceive models into generating perilous responses. Such jailbreaks can trick LLMs into providing intricate instructions to a malicious user…

Computation and Language · Computer Science 2023-11-08 Gabriel Alon , Michael Kamfonas

Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which slight input perturbations can lead to harmful or misleading…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Minkyoung Kim , Yunha Kim , Hyeram Seo , Heejung Choi , Jiye Han , Gaeun Kee , Soyoung Ko , HyoJe Jung , Byeolhee Kim , Young-Hak Kim , Sanghyun Park , Tae Joon Jun

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

Reward models are central to aligning large language models, yet they often overfit to spurious cues such as response length and overly agreeable tone. Most prior work weakens these cues directly by penalizing or controlling specific…

Computation and Language · Computer Science 2026-04-17 Yunsheng Lu , Zijiang Yang , Licheng Pan , Zhixuan Chu

Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generate incorrect outputs in the presence of specific, often…

Machine Learning · Computer Science 2025-03-25 Sharon Lin , Krishnamurthy , Dvijotham , Jamie Hayes , Chongyang Shi , Ilia Shumailov , Shuang Song

Machine learning models are increasingly used for software security tasks. These models are commonly trained and evaluated on large Internet-derived datasets, which often contain duplicated or highly similar samples. When such samples are…

Cryptography and Security · Computer Science 2026-02-02 Farnaz Soltaniani , Mohammad Ghafari

Modern language models often have open weights but closed training data. We formalize the problem of data approximation from model weights and propose several baselines and metrics. We develop a gradient-based approach that selects the…

Computation and Language · Computer Science 2025-06-19 John X. Morris , Junjie Oscar Yin , Woojeong Kim , Vitaly Shmatikov , Alexander M. Rush

Many capable large language models (LLMs) are developed via self-supervised pre-training followed by a reinforcement-learning fine-tuning phase, often based on human or AI feedback. During this stage, models may be guided by their inductive…

Large language models have gained significant popularity because of their ability to generate human-like text and potential applications in various fields, such as Software Engineering. Large language models for code are commonly trained on…

Cryptography and Security · Computer Science 2024-01-17 Ali Al-Kaswan , Maliheh Izadi , Arie van Deursen