English
Related papers

Related papers: Navigating the OverKill in Large Language Models

200 papers

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Computation and Language · Computer Science 2024-10-31 Rishabh Adiga , Besmira Nushi , Varun Chandrasekaran

Large language models (LLM) have emerged as a powerful tool for AI, with the key ability of in-context learning (ICL), where they can perform well on unseen tasks based on a brief series of task examples without necessitating any…

Machine Learning · Computer Science 2024-05-31 Zhenmei Shi , Junyi Wei , Zhuoyan Xu , Yingyu Liang

The training data in large language models is key to their success, but it also presents privacy and security risks, as it may contain sensitive information. Detecting pre-training data is crucial for mitigating these concerns. Existing…

Computation and Language · Computer Science 2025-01-16 Cheng Wang , Yiwei Wang , Bryan Hooi , Yujun Cai , Nanyun Peng , Kai-Wei Chang

Most flagship language models generate explicit reasoning chains, enabling inference-time scaling. However, producing these reasoning chains increases token usage (i.e., reasoning tokens), which in turn increases latency and costs. Our…

Machine Learning · Computer Science 2026-02-05 Abhinav Kumar , Jaechul Roh , Ali Naseh , Marzena Karpinska , Mohit Iyyer , Amir Houmansadr , Eugene Bagdasarian

We argue that the relative success of large language models (LLMs) is not a reflection on the symbolic vs. subsymbolic debate but a reflection on employing an appropriate strategy of bottom-up reverse engineering of language at scale.…

Artificial Intelligence · Computer Science 2023-08-29 Walid S. Saba

The recent explosion in the capabilities of large language models has led to a wave of interest in how best to prompt a model to perform a given task. While it may be tempting to simply choose a prompt based on average performance on a…

Machine Learning · Computer Science 2024-03-29 Thomas P. Zollo , Todd Morrill , Zhun Deng , Jake C. Snell , Toniann Pitassi , Richard Zemel

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Cryptography and Security · Computer Science 2024-08-23 Jayaram Raghuram , George Kesidis , David J. Miller

Large language models (LLMs) excel at a range of tasks through in-context learning (ICL), where only a few task examples guide their predictions. However, prior research highlights that LLMs often overlook input-label mapping information in…

Computation and Language · Computer Science 2025-06-10 Keqin Peng , Liang Ding , Yuanxin Ouyang , Meng Fang , Yancheng Yuan , Dacheng Tao

This paper investigates the influence of cognitive biases on Large Language Models (LLMs) outputs. Cognitive biases, such as confirmation and availability biases, can distort user inputs through prompts, potentially leading to unfaithful…

Computation and Language · Computer Science 2025-06-17 Yan Sun , Stanley Kok

With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is imperative. For example, a company deploying a client-facing chatbot must ensure that…

Computation and Language · Computer Science 2023-06-30 Neel Jain , Khalid Saifullah , Yuxin Wen , John Kirchenbauer , Manli Shu , Aniruddha Saha , Micah Goldblum , Jonas Geiping , Tom Goldstein

Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As…

Machine Learning · Computer Science 2025-06-06 Nikolaus Howe , Ian McKenzie , Oskar Hollinsworth , Michał Zajac , Tom Tseng , Aaron Tucker , Pierre-Luc Bacon , Adam Gleave

Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at training time and rely on additional high-quality data,…

Artificial Intelligence · Computer Science 2026-02-25 Baolong Bi , Yuyao Ge , Shenghua Liu , Yuchen He , Siqian Tong , Lizhe Chen , Lingrui Mei , Zehao Li , Yiwei Wang , Yujun Cai , Ming-Hsuan Yang , Xueqi Cheng

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

Despite significant investment into safety training, large language models (LLMs) deployed in the real world still suffer from numerous vulnerabilities. One perspective on LLM safety training is that it algorithmically forbids the model…

Machine Learning · Computer Science 2024-02-09 Sophie Xhonneux , David Dobre , Jian Tang , Gauthier Gidel , Dhanya Sridhar

Big-data applications often involve a vast number of observations and features, creating new challenges for variable selection and parameter estimation. This paper presents a novel technique called ``slow kill,'' which utilizes nonconvex…

Machine Learning · Statistics 2023-05-04 Yiyuan She , Jianhui Shen , Adrian Barbu

Large Language Models are widely used for content moderation but often present certain over-sensitivity, leading to misclassification of benign content and rejecting safe user commands. While previous research attributes this issue…

Computation and Language · Computer Science 2026-03-19 Yuxin Wang , Botao Yu , Ivory Yang , Saeed Hassanpour , Soroush Vosoughi

Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. While several defenses have been proposed, our…

Artificial Intelligence · Computer Science 2025-09-08 Tiansheng Huang , Gautam Bhattacharya , Pratik Joshi , Josh Kimball , Ling Liu

Large Language Models (LLMs) are implicit troublemakers. While they provide valuable insights and assist in problem-solving, they can also potentially serve as a resource for malicious activities. Implementing safety alignment could…

Cryptography and Security · Computer Science 2024-08-27 Haoyu Wang , Bingzhe Wu , Yatao Bian , Yongzhe Chang , Xueqian Wang , Peilin Zhao

Current social bias benchmarks for Large Language Models (LLMs) primarily rely on predefined question formats like multiple-choice, limiting their ability to reflect the complexity and open-ended nature of real-world interactions. To close…

Computation and Language · Computer Science 2025-10-16 Zhao Liu , Tian Xie , Xueru Zhang

Prompting methods play a crucial role in enhancing the capabilities of pre-trained large language models (LLMs). We explore how contrastive prompting (CP) significantly improves the ability of large language models to perform complex…

Computation and Language · Computer Science 2026-03-06 Liang Yao