English
Related papers

Related papers: ICLShield: Exploring and Mitigating In-Context Lea…

200 papers

We investigate whether chemical processes can perform in-context learning (ICL), a mode of computation typically associated with transformer architectures. ICL allows a system to infer task-specific rules from a sequence of examples without…

Disordered Systems and Neural Networks · Physics 2026-01-13 Carlos Floyd , Hector Manuel Lopez Rios , Aaron R. Dinner , Suriyanarayanan Vaikuntanathan

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Haoyu Wang , Haonan Wang , Yuyan Chen , Jun Chen , Gang Liu , Qian Wang , Jiahong Yan , Yanghua Xiao

Despite their superior performance on a wide range of domains, large language models (LLMs) remain vulnerable to misuse for generating harmful content, a risk that has been further amplified by various jailbreak attacks. Existing jailbreak…

Cryptography and Security · Computer Science 2025-10-27 Yukun Jiang , Mingjie Li , Michael Backes , Yang Zhang

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

Artificial Intelligence · Computer Science 2026-01-06 Josef Ott

Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering…

Machine Learning · Computer Science 2024-12-18 Trang Nguyen , Anh Tran , Nhat Ho

While many-shot ICL achieves remarkable performance, prior studies of its scaling behavior have mainly focused on non-reasoning tasks. In this work, we study many-shot ICL on reasoning tasks, with a particular focus on many-shot…

Computation and Language · Computer Science 2026-05-29 Tsz Ting Chung , Lemao Liu , Mo Yu , Dit-Yan Yeung

The in-context learning (ICL) capability of large language models (LLMs) enables them to perform challenging tasks using provided demonstrations. However, ICL is highly sensitive to the ordering of demonstrations, leading to instability in…

Machine Learning · Computer Science 2025-02-21 Liang Chen , Li Shen , Yang Deng , Xiaoyan Zhao , Bin Liang , Kam-Fai Wong

In a federated learning (FL) system, malicious participants can easily embed backdoors into the aggregated model while maintaining the model's performance on the main task. To this end, various defenses, including training stage…

Machine Learning · Computer Science 2023-05-30 Henger Li , Chen Wu , Sencun Zhu , Zizhan Zheng

Large language models adapt to new tasks through in-context learning (ICL) without parameter updates. Current theoretical explanations for this capability assume test tasks are drawn from a distribution similar to that seen during…

Machine Learning · Computer Science 2026-02-23 Di Zhang

In-Context Learning (ICL) is an emergent capability of Large Language Models (LLMs). Only a few demonstrations enable LLMs to be used as blackbox for new tasks. Previous studies have shown that using LLMs' outputs as labels is effective in…

Computation and Language · Computer Science 2024-04-04 Kazuma Hashimoto , Karthik Raman , Michael Bendersky

Large language models (LLMs) have shown an impressive ability to perform a wide range of tasks using in-context learning (ICL), where a few examples are used to describe a task to the model. However, the performance of ICL varies…

Computation and Language · Computer Science 2024-06-25 Keqin Peng , Liang Ding , Yancheng Yuan , Xuebo Liu , Min Zhang , Yuanxin Ouyang , Dacheng Tao

In-context learning (ICL) is a new paradigm for natural language processing (NLP), where a large language model (LLM) observes a small number of demonstrations and a test instance as its input, and directly makes predictions without…

Computation and Language · Computer Science 2024-12-12 Fei Zhao , Taotian Pang , Zhen Wu , Zheng Ma , Shujian Huang , Xinyu Dai

Large Language Models (LLMs) have proven effective at In-Context Learning (ICL), an ability that allows them to create predictors from labeled examples. Few studies have explored the interplay between ICL and specific properties of…

Machine Learning · Computer Science 2023-11-23 David Oniani , Yanshan Wang

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

In-Context Learning (ICL) has emerged as a promising solution to enhance the code generation capabilities of Large Language Models (LLMs), which incorporates code examples inside the prompt to let LLMs learn from demonstrations. However,…

Software Engineering · Computer Science 2025-08-11 Dongze Li , Songqiang Chen , Jialun Cao , Shing-Chi Cheung

Masked image modeling (MIM) revolutionizes self-supervised learning (SSL) for image pre-training. In contrast to previous dominating self-supervised methods, i.e., contrastive learning, MIM attains state-of-the-art performance by masking…

Cryptography and Security · Computer Science 2022-10-05 Xinyue Shen , Xinlei He , Zheng Li , Yun Shen , Michael Backes , Yang Zhang

Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing…

Computation and Language · Computer Science 2025-11-04 Peng Ding , Jun Kuang , Wen Sun , Zongyu Wang , Xuezhi Cao , Xunliang Cai , Jiajun Chen , Shujian Huang

In-context learning (ICL) is one of the most powerful and most unexpected capabilities to emerge in recent transformer-based large language models (LLMs). Yet the mechanisms that underlie it are poorly understood. In this paper, we…

Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or…

Cryptography and Security · Computer Science 2025-05-21 Tiehan Cui , Yanxu Mao , Peipei Liu , Congying Liu , Datao You

Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations without the need for parameter updates. However, many studies…

Computation and Language · Computer Science 2024-06-04 Yi Su , Yunpeng Tai , Yixin Ji , Juntao Li , Bowen Yan , Min Zhang