English
Related papers

Related papers: Jailbreak and Guard Aligned Language Models with O…

200 papers

Large language models (LLMs) such as GPT-3 and GPT-4 are powerful but their weights are often publicly unavailable and their immense sizes make the models difficult to be tuned with common hardware. As a result, effectively tuning these…

Computation and Language · Computer Science 2023-05-16 Canwen Xu , Yichong Xu , Shuohang Wang , Yang Liu , Chenguang Zhu , Julian McAuley

In-context learning (ICL) has emerged as an effective approach to enhance the performance of large language models (LLMs). However, its effectiveness varies significantly across models and tasks, posing challenges for practitioners to…

Computation and Language · Computer Science 2025-07-15 Dingzriui Wang , Xuanliang Zhang , Keyan Xu , Qingfu Zhu , Wanxiang Che , Yang Deng

In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs. Evaluating the ICL ability of LLMs can enhance their utilization and deepen our…

Computation and Language · Computer Science 2024-12-10 Wentong Chen , Yankai Lin , ZhenHao Zhou , HongYun Huang , Yantao Jia , Zhao Cao , Ji-Rong Wen

Large Language Models (LLMs) have gained widespread adoption across various domains, including chatbots and auto-task completion agents. However, these models are susceptible to safety vulnerabilities such as jailbreaking, prompt injection,…

Cryptography and Security · Computer Science 2024-09-10 Divyanshu Kumar , Anurakt Kumar , Sahil Agarwal , Prashanth Harshangi

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

Cryptography and Security · Computer Science 2026-01-01 Yuan Xin , Dingfan Chen , Linyi Yang , Michael Backes , Xiao Zhang

Large language models have drawn significant attention to the challenge of safe alignment, especially regarding jailbreak attacks that circumvent security measures to produce harmful content. To address the limitations of existing methods…

Artificial Intelligence · Computer Science 2024-11-05 Hanqing Liu , Lifeng Zhou , Huanqian Yan

Recent interest has surged in employing Large Language Models (LLMs) for machine translation (MT) via in-context learning (ICL) (Vilar et al., 2023). Most prior studies primarily focus on optimizing translation quality, with limited…

Computation and Language · Computer Science 2024-06-06 Pranjal A. Chitale , Jay Gala , Raj Dabre

In-context learning (ICL) is a crucial capability of current large language models (LLMs), where the selection of examples plays a key role in performance. While most existing approaches focus on selecting the most similar examples to the…

Computation and Language · Computer Science 2025-06-06 Wenyang Xiao , Haoyu Zhao , Lingxiao Huang

Large Language Models (LLMs) have become ubiquitous in NLP and deep learning. In-Context Learning (ICL) has been suggested as a bridging paradigm between the training-free and fine-tuning LLMs settings. In ICL, an LLM is conditioned to…

Computation and Language · Computer Science 2024-06-12 Jérémie Cabessa , Hugo Hernault , Umer Mushtaq

In-context learning (ICL) empowers large language models (LLMs) to perform diverse tasks in underrepresented languages using only short in-context information, offering a crucial avenue for narrowing the gap between high-resource and…

Computation and Language · Computer Science 2024-06-26 Samuel Cahyawijaya , Holy Lovenia , Pascale Fung

Large language models (LLMs) are capable to perform complex reasoning by in-context learning (ICL) when provided with a few input-output demonstrations (demos) and more powerful when intermediate reasoning steps ("chain of thoughts (CoT)")…

Artificial Intelligence · Computer Science 2023-04-26 Jiuhai Chen , Lichang Chen , Chen Zhu , Tianyi Zhou

In-Context Learning (ICL) empowers Large Language Models (LLMs) with the ability to learn from a few examples provided in the prompt, enabling downstream generalization without the requirement for gradient updates. Despite encouragingly…

Computation and Language · Computer Science 2025-01-28 Haitao Mao , Guangliang Liu , Yao Ma , Rongrong Wang , Kristen Johnson , Jiliang Tang

Jailbreaks on large language models (LLMs) have recently received increasing attention. For a comprehensive assessment of LLM safety, it is essential to consider jailbreaks with diverse attributes, such as contextual coherence and…

Machine Learning · Computer Science 2024-06-10 Xingang Guo , Fangxu Yu , Huan Zhang , Lianhui Qin , Bin Hu

Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into…

Cryptography and Security · Computer Science 2026-02-17 Shang Liu , Hanyu Pei , Zeyan Liu

In-context learning (ICL) is now a common method for teaching large language models (LLMs) new tasks: given labeled examples in the input context, the LLM learns to perform the task without weight updates. Do models guided via ICL infer the…

Computation and Language · Computer Science 2024-04-11 Aaron Mueller , Albert Webson , Jackson Petty , Tal Linzen

Large Language Models (LLMs) have shown strong in-context learning (ICL) abilities with a few demonstrations. However, one critical challenge is how to select demonstrations to elicit the full potential of LLMs. In this paper, we propose…

Computation and Language · Computer Science 2024-12-17 Duc Anh Vu , Nguyen Tran Cong Duy , Xiaobao Wu , Hoang Minh Nhat , Du Mingzhe , Nguyen Thanh Thong , Anh Tuan Luu

Large language models (LLMs) are able to solve various tasks with only a few demonstrations utilizing their in-context learning (ICL) abilities. However, LLMs often rely on their pre-trained semantic priors of demonstrations rather than on…

Computation and Language · Computer Science 2024-04-16 Joonwon Jang , Sanghwan Jang , Wonbin Kweon , Minjin Jeon , Hwanjo Yu

Large language models (LLMs) famously exhibit emergent in-context learning (ICL) -- the ability to rapidly adapt to new tasks using few-shot examples provided as a prompt, without updating the model's weights. Built on top of LLMs, vision…

Machine Learning · Computer Science 2025-04-02 Yongshuo Zong , Ondrej Bohdal , Timothy Hospedales

In-Context Learning (ICL) empowers Large Language Models (LLMs) for rapid task adaptation without Fine-Tuning (FT), but its reliance on demonstration selection remains a critical challenge. While many-shot ICL shows promising performance…

Computation and Language · Computer Science 2025-06-06 Jianfei Zhang , Bei Li , Jun Bai , Rumei Li , Yanmeng Wang , Chenghua Lin , Wenge Rong

The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak…

Computation and Language · Computer Science 2024-03-25 Zezhong Wang , Fangkai Yang , Lu Wang , Pu Zhao , Hongru Wang , Liang Chen , Qingwei Lin , Kam-Fai Wong