English
Related papers

Related papers: Incomplete Tasks Induce Shutdown Resistance in Som…

200 papers

In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term \textbf{involuntary jailbreak}. Unlike existing jailbreak attacks, this weakness is distinct in that it does not involve a specific…

Cryptography and Security · Computer Science 2025-12-30 Yangyang Guo , Yangyan Li , Mohan Kankanhalli

With the incredible advancements in Large Language Models (LLMs), many people have started using them to satisfy their information needs. However, utilizing LLMs might be problematic for political issues where disagreement is common and…

Computers and Society · Computer Science 2026-01-27 Salah Feras Alali , Mohammad Nashat Maasfeh , Mucahid Kutlu , Saban Kardas

Large Language Models (LLMs) often exhibit behavioral artifacts such as laziness (premature truncation of responses or partial compliance with multi-part requests), decoding suboptimality (failure to select higher-quality sequences due to…

Artificial Intelligence · Computer Science 2025-12-25 Yiqing Ma , Jung-Hua Liu

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…

Cryptography and Security · Computer Science 2026-02-27 Piyush Jaiswal , Aaditya Pratap , Shreyansh Saraswati , Harsh Kasyap , Somanath Tripathy

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

Computation and Language · Computer Science 2026-04-29 Nirmalendu Prakash , Yeo Wei Jie , Amir Abdullah , Ranjan Satapathy , Erik Cambria , Roy Ka Wei Lee

What kinds of instructional prompts are easier to follow for Language Models (LMs)? We study this question by conducting extensive empirical analysis that shed light on important features of successful instructional prompts. Specifically,…

Computation and Language · Computer Science 2022-03-17 Swaroop Mishra , Daniel Khashabi , Chitta Baral , Yejin Choi , Hannaneh Hajishirzi

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

Computation and Language · Computer Science 2026-04-21 Yuheng Chen , Zhiyu Wu , Bowen Cheng , Tetsuro Takahashi

Small open-source language models are gaining attention for healthcare applications in low-resource settings where cloud infrastructure and GPU hardware may be unavailable. However, the reliability of these models under different phrasings…

Computation and Language · Computer Science 2026-03-18 Shravani Hariprasad

Large Language Models (LLMs) have showcased remarkable capabilities in following human instructions. However, recent studies have raised concerns about the robustness of LLMs when prompted with instructions combining textual adversarial…

Computation and Language · Computer Science 2024-02-27 Yuansen Zhang , Xiao Wang , Zhiheng Xi , Han Xia , Tao Gui , Qi Zhang , Xuanjing Huang

In an era where large language models (LLMs) are increasingly integrated into a wide range of everyday applications, research into these models' behavior has surged. However, due to the novelty of the field, clear methodological guidelines…

Computation and Language · Computer Science 2024-10-01 Laurène Vaugrante , Mathias Niepert , Thilo Hagendorff

Prompt injection evaluations typically treat refusal as a stable, binary indicator of safety. This study challenges that paradigm by modeling refusal as a local decision boundary and examining its stability under structured perturbations.…

Cryptography and Security · Computer Science 2026-01-27 Thomas Heverin

Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations…

Computation and Language · Computer Science 2022-05-24 Or Honovich , Uri Shaham , Samuel R. Bowman , Omer Levy

Previous work has shown that there exists a scaling law between the size of Language Models (LMs) and their zero-shot performance on different downstream NLP tasks. In this work, we show that this phenomenon does not hold when evaluating…

Computation and Language · Computer Science 2022-09-27 Joel Jang , Seonghyeon Ye , Minjoon Seo

In this paper, we present a benchmark to pressure-test today's frontier models' multimodal decision-making capabilities in the very long-context regime (up to one million tokens) and investigate whether these models can learn from large…

Artificial Intelligence · Computer Science 2025-05-26 Anian Ruoss , Fabio Pardo , Harris Chan , Bonnie Li , Volodymyr Mnih , Tim Genewein

Frontier large language models are increasingly deployed as orchestration backbones for biological research workflows, yet no shared evidence base exists for comparing their refusal behaviour on legitimate research prompts. RefusalBench,…

Software Engineering · Computer Science 2026-05-22 Lukas Weidener , Marko Brkić , Mihailo Jovanović , Emre Ulgac , Aakaash Meduri

Large Language Models (LLMs) have demonstrated exceptional proficiency in instruction-following, becoming increasingly crucial across various applications. However, this capability brings with it the risk of prompt injection attacks, where…

Computation and Language · Computer Science 2023-11-28 Zekun Li , Baolin Peng , Pengcheng He , Xifeng Yan

The rapid advancements in large language models (LLMs) have greatly expanded the potential for automated code-related tasks. Two primary methodologies are used in this domain: prompt engineering and fine-tuning. Prompt engineering involves…

Software Engineering · Computer Science 2025-02-21 Jiho Shin , Clark Tang , Tahmineh Mohati , Maleknaz Nayebi , Song Wang , Hadi Hemmati

Prompt engineering reduces reasoning mistakes in Large Language Models (LLMs). However, its effectiveness in mitigating vulnerabilities in LLM-generated code remains underexplored. To address this gap, we implemented a benchmark to…

Software Engineering · Computer Science 2025-02-11 Marc Bruni , Fabio Gabrielli , Mohammad Ghafari , Martin Kropp

Large language models (LLMs) are typically prompted to follow a single instruction per inference call. In this work, we analyze whether LLMs also hold the capability to handle multiple instructions simultaneously, denoted as Multi-Task…

Computation and Language · Computer Science 2024-06-07 Guijin Son , Sangwon Baek , Sangdae Nam , Ilgyun Jeong , Seungone Kim

AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We…

Artificial Intelligence · Computer Science 2026-05-08 Jonas Wiedermann-Möller , Leonard Dung , Maksym Andriushchenko