检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ding, Hanxing Tao, Shuchang Pang, Liang Wei, Zihao Gao, Jinyang Ding, Bolin Shen, Huawei Cheng, Xueqi Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Alibaba Group China

Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools. Existing approaches face significant challenges, including reliance on hand-crafted prompts, difficulty in multi-step planning, and lack of precise error diagnosis and reflection mechanisms. We propose ToolCoder, a novel framework that reformulates tool learning as a code generation task. Inspired by software engineering principles, ToolCoder transforms natural language queries into structured Python function scaffold and systematically breaks down tasks with descriptive comments, enabling LLMs to leverage coding paradigms for complex reasoning and planning. It then generates and executes function implementations to obtain final responses. Additionally, ToolCoder stores successfully executed functions in a repository to promote code reuse, while leveraging error traceback mechanisms for systematic debugging, optimizing both execution efficiency and robustness. Experiments demonstrate that ToolCoder achieves superior performance in task completion accuracy and execution reliability compared to existing approaches, establishing the effectiveness of code-centric approaches in tool learning. Our code is available at this link. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The 1st Workshop on Human-Centered Recommender Systems 25

The 1st Workshop on Human-Centered Recommender Systems

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Kaike Zhang Yunfan Wu Yougang Lyu Du Su Yingqiang Ge Shuchang Liu Qi Cao Zhaochun Ren Fei Sun University of Chinese Academy of Sciences Beijing China University of Amsterdam Amsterdam Netherlands CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China Amazon New Brunswick USA Kuaishou Beijing China Leiden University Leiden Netherlands

ISBN: (纸本)9798400713316

Recommender systems are quintessential applications of human-computer interaction. Widely utilized in daily life, they offer significant convenience but also present numerous challenges, such as the information cocoon effect, privacy concerns, fairness issues, and more. Consequently, this workshop aims to provide a platform for researchers to explore the development of Human-Centered Recommender Systems (HCRS). HCRS refers to the creation of recommender systems that prioritize human needs, values, and capabilities at the core of their design and operation. In this workshop, topics will include, but are not limited to, robustness, privacy, transparency, fairness, diversity, accountability, ethical considerations, and user-friendly design. We hope to engage in discussions on how to implement and enhance these properties in recommender systems. Additionally, participants will explore diverse evaluation methods, including innovative metrics that capture user satisfaction and trust. This workshop seeks to foster a collaborative environment for researchers to share insights and advance the field toward more ethical, user-centric, and socially responsible recommender systems.

关键词： ethics

来源：评论

学校读者我要写书评

暂无评论

Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models

arXiv

引用

arXiv 2025年

作者： Xu, Yilong Gao, Jinhua Yu, Xiaoming Xue, Yuanhai Bi, Baolong Shen, Huawei Cheng, Xueqi State Key Lab of AI Safety Institute of Computing Technology CAS China Key Lab of AI Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Retrieval-Augmented Language Models boost task performance, owing to the retriever that provides external knowledge. Although crucial, the retriever primarily focuses on semantics relevance, which may not always be effective for generation. Thus, utility-based retrieval has emerged as a promising topic, prioritizing passages that provides valid benefits for downstream tasks. However, due to insufficient understanding, capturing passage utility accurately remains unexplored. This work proposes SCARLet, a framework for training utility-based retrievers in RALMs, which incorporates two key factors, multi-task generalization and inter-passage interaction. First, SCARLet constructs shared context on which training data for various tasks is synthesized. This mitigates semantic bias from context differences, allowing retrievers to focus on learning task-specific utility for better task generalization. Next, SCARLet uses a perturbation-based attribution method to estimate passage-level utility for shared context, which reflects interactions between passages and provides more accurate feedback. We evaluate our approach on ten datasets across various tasks, both in-domain and out-of-domain, showing that retrievers trained by SCARLet consistently improve the overall performance of RALMs. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GNN-Based Persistent K-core Community Search in Temporal Graphs

GNN-Based Persistent K-core Community Search in Temporal Gra...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Jiang, Zongli Tan, Yirui Chen, Guoxin Guo, Fangda Zhang, Jinli Bai, Xiaolu Beijing University of Technology Beijing China Institute of Computing Technology Cas University of Chinese Academy of Sciences Key Laboratory of Ai Safety Beijing China Institute of Computing Technology Cas Key Laboratory of Ai Safety Beijing China

ISBN: (纸本)9798350362480

The goal of community search is to provide effective solutions for real-time, high-quality community searches within large networks. In many practical applications, such as event organization and friend recommendations, discovering various community structures within a network is crucial for users. However, existing community search algorithms rarely address issues within temporal graphs, and those that do often have two main limitations: (1) traditional community search methods become inefficient and experience significant increases in computation time when scaled to large graphs;(2) while GNN-based community search methods for temporal graphs offer generalizability, they often focus solely on community connectivity and lack cohesiveness. Therefore, we propose a new model PK-GCN, based on Graph Neural Networks (GNNs), to identify persistent k-core communities in temporal networks. This model can handle dynamic changes in temporal graphs and identify communities that persist over time. Compared to existing community search methods, our model not only finds communities with tighter structures but also allows for dynamic queries based on user input without needing retraining. Specifically, our model constructs features by integrating k-core information from core decomposition, graph features, and query features, resulting in more expressive node representations. Additionally, we designed a flexible dynamic query mechanism that allows users to input time information to query communities. Experiments on multiple datasets demonstrate that our model outperforms other GNN-based community search algorithms in F1-score. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Leveraging face-prior knowledge for general face representation learning

引用

Pattern Recognition 2025年 168卷

作者： Haomiao Sun Mingjie He Shiguang Shan Hu Han State Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China

Face analysis, such as face attribute recognition and expression classification, has achieved remarkable progress via supervised deep learning methods. Although effective, supervised learning relies on a large amount of annotated data, which is labor-intensive. Besides, traditional models designed for individual tasks cannot generate a general facial representation that can be applied across multiple tasks. To address these issues, we present a novel general face representation learning method that empowers diverse face analysis tasks by incorporating auxiliary tasks with face-prior knowledge. Our approach employs three auxiliary tasks at pixel, patch, and component levels to exploit information from face images, enabling the model to learn multi-level face representations beneficial to diverse downstream tasks. We evaluate the efficacy of our approach on various downstream face analysis tasks, including facial action unit detection, expression classification, age estimation, and face attribute recognition. Specifically, our method surpasses the state-of-the-art by 3.5% for action unit detection and 1.53% for expression classification. On the AgeDB dataset, our method reduces the mean error by 0.64. Furthermore, in face attribute classification tasks, our model also achieves state-of-the-art performance. Experimental results also show that our proposed method outperforms previous methods under both full-shot and few-shot protocols.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense 38

CausalDiff: Causality-Inspired Disentanglement via Diffusion...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Mingkun Bi, Keping Chen, Wei Chen, Quanrun Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China Key Laboratory of Network Data Science and Technology Institute of Computing Technology CAS China School of Statistics University of International Business and Economics China

Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark). The code is available at https://***/cas-aisafetyBasicResearchGroup/CausalDiff. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection

arXiv

引用

arXiv 2025年

作者： Li, Yong Liu, Menglin Cui, Zhen Ding, Yi Zong, Yuan Zheng, Wenming Shan, Shiguang Guan, Cuntai School of Computer Science and Engineering The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing210096 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Artificial Intelligence Beijing Normal University Beijing100875 China Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China School of Computer Science and Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Key Laboratory of Child Development and Learning Science of Ministry of Education School of Biological Science and Medical Engineering Nanjing210096 China

Despite the impressive performance of current vision-based facial action unit (AU) detection approaches, they are heavily susceptible to the variations across different domains and the cross-domain AU detection methods are under-explored. In response to this challenge, we propose a decoupled doubly contrastive adaptation (D2CA) approach to learn a purified AU representation that is semantically aligned for the source and target domains. Specifically, we decompose latent representations into AU-relevant and AU-irrelevant components, with the objective of exclusively facilitating adaptation within the AU-relevant subspace. To achieve the feature decoupling, D2CA is trained to disentangle AU and domain factors by assessing the quality of synthesized faces in cross-domain scenarios when either AU or domain attributes are modified. To further strengthen feature decoupling, particularly in scenarios with limited AU data diversity, D2CA employs a doubly contrastive learning mechanism comprising image and feature-level contrastive learning to ensure the quality of synthesized faces and mitigate feature ambiguities. This new framework leads to an automatically learned, dedicated separation of AU-relevant and domain-relevant factors, and it enables intuitive, scale-specific control of the cross-domain facial image synthesis. Extensive experiments demonstrate the efficacy of D2CA in successfully decoupling AU and domain factors, yielding visually pleasing cross-domain synthesized facial images. Meanwhile, D2CA consistently outperforms state-of-the-art cross-domain AU detection approaches, achieving an average F1 score improvement of 6%-14% across various cross-domain scenarios. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression

arXiv

引用

arXiv 2025年

作者： Chen, Lizhe Zhou, Binjia Ge, Yuyao Chen, Jiayi Ni, Shiguang Shenzhen International Graduate School Tsinghua University China Zhejiang University China CAS Key Laboratory of AI Security Institute of Computing Technology Chinese Academy of Sciences China Fudan University China

Large language models (LLMs) have achieved remarkable progress, demonstrating unprecedented capabilities across various natural language processing tasks. However, the high costs associated with such exceptional performance limit the widespread adoption of LLMs, highlighting the need for prompt compression. Existing prompt compression methods primarily rely on heuristic truncation or abstractive summarization techniques, which fundamentally overlook the intrinsic mechanisms of LLMs and lack a systematic evaluation of token importance for generation. In this work, we introduce Prompt Importance Sampling (PIS), a novel compression framework that dynamically compresses prompts by sampling important tokens based on the analysis of attention scores of hidden states. PIS employs a dual-level compression mechanism: 1) at the token level, we quantify saliency using LLM-native attention scores and implement adaptive compression through a lightweight 9-layer reinforcement learning network;2) at the semantic level, we propose a Russian roulette sampling strategy for sentence-level importance sampling. Comprehensive evaluations across multiple domain benchmarks demonstrate that our method achieves state-of-the-art compression performance. In particular, our framework improves reasoning efficiency to some extent through optimized context structuring. This work advances prompt engineering by offering both theoretical grounding and practical efficiency in context management for LLMs. © 2025, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Plot Retrieval as an Assessment of Abstract Semantic Association 62

Plot Retrieval as an Assessment of Abstract Semantic Associa...

引用

62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Xu, Shicheng Pang, Liang Li, Jiangnan Yu, Mo Meng, Fandong Shen, Huawei Cheng, Xueqi Zhou, Jie CAS Key Laboratory of AI Security Institute of Computing Technology CAS China Pattern Recognition Center WeChat AI

ISBN: (纸本)9798891760974

Retrieving relevant plots from the book for a query is a critical task, which can improve the reading experience and efficiency of readers. Readers usually only give an abstract and vague description as the query based on their own understanding, summaries, or speculations of the plot, which requires the retrieval model to have a strong ability to estimate the abstract semantic associations between the query and candidate plots. However, existing information retrieval (IR) datasets cannot reflect this ability well. In this paper, we propose PLOTRETRIEVAL, a labeled dataset to train and evaluate the performance of IR models on the novel task Plot Retrieval. Text pairs in PLOTRETRIEVAL have less word overlap and more abstract semantic association, which can reflect the ability of the IR models to estimate the abstract semantic association, rather than just traditional lexical or semantic matching. Extensive experiments across various lexical retrieval, sparse retrieval, dense retrieval, and cross-encoder methods compared with human studies on PLOTRETRIEVAL show current IR models still struggle in capturing abstract semantic association between texts. PLOTRETRIEVAL can be the benchmark for further research on the semantic association modeling ability of IR models. ©2024 Association for Computational Linguistics.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

The Fall of ROME: Understanding the Collapse of LLMs in Model Editing

The Fall of ROME: Understanding the Collapse of LLMs in Mode...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Yang, Wanli Sun, Fei Tan, Jiajun Ma, Xinyu Su, Du Yin, Dawei Shen, Huawei CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China University of Chinese Academy of Sciences China Baidu Inc. China

ISBN: (纸本)9798891761681

Despite significant progress in model editing methods, their application in real-world scenarios remains challenging as they often cause large language models (LLMs) to collapse. Among them, ROME is particularly concerning, as it could disrupt LLMs with only a single edit. In this paper, we study the root causes of such collapse. Through extensive analysis, we identify two primary factors that contribute to the collapse: i) inconsistent handling of prefixed and unprefixed keys in the parameter update equation may result in very small denominators, causing excessively large parameter updates;ii) the subject of collapse cases is usually the first token, whose unprefixed key distribution significantly differs from the prefixed key distribution in autoregressive transformers, causing the aforementioned issue to materialize. To validate our findings, we propose a simple yet effective approach: uniformly using prefixed keys during editing phase and adding prefixes during testing phase to ensure the consistency between training and testing. The experimental results show that the proposed solution can prevent model collapse while maintaining the effectiveness of the edits. © 2024 Association for Computational Linguistics.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：