English
Related papers

Related papers: CRaFT: Circuit-Guided Refusal Feature Selection vi…

200 papers

Retrieval-augmented large language models, when optimized with outcome-level rewards, can achieve strong answer accuracy on multi-hop questions. However, under noisy retrieval, models frequently suffer from "right-answer-wrong-reason…

Computation and Language · Computer Science 2026-03-17 Yu Liu , Wenxiao Zhang , Diandian Guo , Cong Cao , Fangfang Yuan , Qiang Sun , Yanbing Liu , Jin B. Hong , Zhiyuan Ma

In order to efficiently use the future generations of supercomputers, fault tolerance and power consumption are two of the prime challenges anticipated by the High Performance Computing (HPC) community. Checkpoint/Restart (CR) has been and…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-08-08 Faisal Shahzad , Jonas Thies , Moritz Kreutzer , Thomas Zeiser , Georg Hager , Gerhard Wellein

Industrial multi-label document understanding pipelines score candidate labels and threshold or rank them to form a label set per document. This early selection step directly affects the accuracy of downstream information extraction from…

Information Retrieval · Computer Science 2026-05-19 Lasal Jayawardena , Nirmalie Wiratunga , Ikechukwu Nkisi-Orji , Darren Nicol

The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit…

Machine Learning · Computer Science 2026-04-07 Lin Wang , Junfeng Fang , Dan Zhang , Fei Shen , Xiang Wang , Tat-Seng Chua

Despite the outstanding performance of Large language Models (LLMs) in diverse tasks, they are vulnerable to jailbreak attacks, wherein adversarial prompts are crafted to bypass their security mechanisms and elicit unexpected responses.…

Cryptography and Security · Computer Science 2025-04-25 Zeqing He , Zhibo Wang , Zhixuan Chu , Huiyu Xu , Wenhui Zhang , Qinglong Wang , Rui Zheng

Online multi-object tracking (MOT) is an active research topic in the domain of computer vision. Although many previously proposed algorithms have exhibited decent results, the issue of tracklet inactivation has not been sufficiently…

Computer Vision and Pattern Recognition · Computer Science 2021-04-26 Tianze Gao , Huihui Pan , Zidong Wang , Huijun Gao

Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from…

Artificial Intelligence · Computer Science 2025-09-30 Zhaoqi Wang , Daqing He , Zijian Zhang , Xin Li , Liehuang Zhu , Meng Li , Jiamou Liu

Survival analysis is complicated by censored data, high-dimensional features, and non-linear interactions. Classical models offer interpretability and superior calibration but are restricted to linear or predefined functional forms, while…

Machine Learning · Computer Science 2026-05-19 Mohammad Ashhad , Robert Hoehndorf , Ricardo Henao

We consider two-class linear classification in a high-dimensional, low-sample size setting. Only a small fraction of the features are useful, the useful features are unknown to us, and each useful feature contributes weakly to the…

Statistics Theory · Mathematics 2015-05-13 David Donoho , Jiashun Jin

In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly…

Artificial Intelligence · Computer Science 2026-05-28 Matteo Gioele Collu , Riccardo Conte , Alberto Giaretta , Denis Kleyko , Mauro Conti , Matteo Zavatteri , Roberto Confalonieri

Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem…

Artificial Intelligence · Computer Science 2026-03-13 Zhiyu Xue , Zimo Qi , Guangliang Liu , Bocheng Chen , Ramtin Pedarsani

Recent advancements in recommender systems have focused on leveraging Large Language Models (LLMs) to improve user preference modeling, yielding promising outcomes. However, current LLM-based approaches struggle to fully leverage user…

Information Retrieval · Computer Science 2024-10-31 Yang Zhang , Juntao You , Yimeng Bai , Jizhi Zhang , Keqin Bao , Wenjie Wang , Tat-Seng Chua

Large language models (LLMs) are often augmented with tools to solve complex tasks. By generating code snippets and executing them through task-specific Application Programming Interfaces (APIs), they can offload certain functions to…

Computation and Language · Computer Science 2024-03-14 Lifan Yuan , Yangyi Chen , Xingyao Wang , Yi R. Fung , Hao Peng , Heng Ji

Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. We present RAID (Refusal-Aware and Integrated Decoding), a framework that…

Computation and Language · Computer Science 2025-12-23 Tuan T. Nguyen , John Le , Thai T. Vu , Willy Susilo , Heath Cooper

Deploying LLMs in multi-turn dialogues facilitates jailbreak attacks that distribute harmful intent across seemingly benign turns. Recent training-based multi-turn jailbreak methods learn long-horizon attack strategies from interaction…

Artificial Intelligence · Computer Science 2026-05-12 Zhida He , Xiaoyu Wen , Han Qi , Ziyuan Zhou , Peng Yu , Xingcheng Xu , Dongrui Liu , Xia Hu , Chaochao Lu , Qiaosheng Zhang

Future link prediction on temporal graphs is a fundamental task with wide applicability in real-world dynamic systems. These scenarios often involve both recurring (seen) and novel (unseen) interactions, requiring models to generalize…

Machine Learning · Computer Science 2025-05-27 Lu Yi , Runlin Lei , Fengran Mo , Yanping Zheng , Zhewei Wei , Yuhang Ye

Large Language Models (LLMs) have transformed task automation and content generation across various domains while incorporating safety filters to prevent misuse. We introduce a novel jailbreaking framework that employs distributed prompt…

Cryptography and Security · Computer Science 2025-04-01 Johan Wahréus , Ahmed Hussain , Panos Papadimitratos

Supervised fine-tuning (SFT) induces new behaviors in large language models, yet imposes no structural constraint on how these behaviors are distributed within the model. Existing behavior interpretation methods, such as circuit attribution…

Machine Learning · Computer Science 2026-05-08 Yuping Lin , Pengfei He , Yue Xing , Yingqian Cui , Jiayuan Ding , Subhabrata Mukherjee , Hui Liu , Zhen Xiang

Learning to compute, the ability to model the functional behavior of a circuit graph, is a fundamental challenge for graph representation learning. Yet, the dominant paradigm is architecturally mismatched for this task. This flawed…

Artificial Intelligence · Computer Science 2026-02-10 Ziyang Zheng , Jiaying Zhu , Jingyi Zhou , Qiang Xu

Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement…

Machine Learning · Computer Science 2026-05-05 Seonglae Cho , Zekun Wu , Adriano Koshiyama