检索结果-内蒙古大学图书馆

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

作者： Wu, Kangxi Pang, Liang Shen, Huawei Cheng, Xueqi Key Laboratory of AI Safety Chinese Academy of Sciences Institute of Computing Technology CAS China University of Chinese Academy of Sciences China

ISBN: (纸本)9798891761643

The black-box nature of large language models (LLMs) poses challenges in interpreting results, impacting issues such as data intellectual property protection and hallucination tracing. Training data attribution (TDA) methods are considered effective solutions to address these challenges. Most recent TDA methods rely on influence functions, assuming the model achieves minimized empirical risk. However, achieving this criterion is difficult, and sourcing accuracy can be compromised by fitting errors during model training. In this paper, we introduce a novel TDA method called Debias and Denoise Attribution (DDA), which enhances influence functions by addressing fitting errors. Specifically, the debias strategy seeks to improve the performance of influence functions by eliminating the knowledge bias present in the base model before fine-tuning, while the denoise strategy aims to reduce discrepancies in influence scores arising from varying degrees of fitting during the training process through smoothing techniques. Experimental results demonstrate that our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%. Moreover, DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral. © 2024 Association for Computational Linguistics.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation 38

Understanding and Improving Adversarial Collaborative Filter...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Kaike Cao, Qi Wu, Yunfan Sun, Fei Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Adversarial Collaborative Filtering (ACF), which typically applies adversarial perturbations at user and item embeddings through adversarial training, is widely recognized as an effective strategy for enhancing the robustness of Collaborative Filtering (CF) recommender systems against poisoning attacks. Besides, numerous studies have empirically shown that ACF can also improve recommendation performance compared to traditional CF. Despite these empirical successes, the theoretical understanding of ACF's effectiveness in terms of both performance and robustness remains unclear. To bridge this gap, in this paper, we first theoretically show that ACF can achieve a lower recommendation error compared to traditional CF with the same training epochs in both clean and poisoned data contexts. Furthermore, by establishing bounds for reductions in recommendation error during ACF's optimization process, we find that applying personalized magnitudes of perturbation for different users based on their embedding scales can further improve ACF's effectiveness. Building on these theoretical understandings, we propose Personalized Magnitude Adversarial Collaborative Filtering (PamaCF). Extensive experiments demonstrate that PamaCF effectively defends against various types of poisoning attacks while significantly enhancing recommendation performance. © 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

PKAD: Pretrained Knowledge is All You Need to Detect and Mitigate Textual Backdoor Attacks

PKAD: Pretrained Knowledge is All You Need to Detect and Mit...

引用

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

作者： Chen, Yu Cao, Qi Zhang, Kaike Liu, Xuchao Shen, Huawei CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761681

In textual backdoor attacks, attackers insert poisoned samples with triggered inputs and target labels into training datasets to manipulate model behavior, threatening the model's security and reliability. Current defense methods can generally be categorized into inference-time and training-time ones. The former often requires a part of clean samples to set detection thresholds, which may be hard to obtain in practical application scenarios, while the latter usually requires an additional retraining or unlearning process to get a clean model, significantly increasing training costs. To avoid these drawbacks, we focus on developing a practical defense method before model training without using any clean samples. Our analysis reveals that with the help of a pretrained language model (PLM), poisoned samples, different from clean ones, exhibit mismatched relationship and shared characteristics. Based on these observations, we further propose a two-stage poison detection strategy solely leveraging insights from PLM before model training. Extensive experiments confirm our approach's effectiveness, achieving better performance than current leading methods more swiftly. Our code is available at https://***/Ascian/PKAD. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Augmentation-Aware Self-Supervision for Data-Efficient GAN Training 37

Augmentation-Aware Self-Supervision for Data-Efficient GAN T...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Hou, Liang Cao, Qi Yuan, Yige Zhao, Songtao Ma, Chongyang Pan, Siyuan Wan, Pengfei Wang, Zhongyuan Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Kuaishou Technology China

ISBN: (纸本)9781713899921

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data. This formulation connects the learning objective of the generator and the arithmetic - harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Qsnail: A Questionnaire Dataset for Sequential Question Generation 30

Qsnail: A Questionnaire Dataset for Sequential Question Gene...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Lei, Yan Pang, Liang Wang, Yuanzhuo Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Safety & Security Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9782493814104

The questionnaire is a professional research methodology used for both qualitative and quantitative analysis of human opinions, preferences, attitudes, and behaviors. However, designing and evaluating questionnaires demands significant effort due to their intricate and complex structure. Questionnaires entail a series of questions that must conform to intricate constraints involving the questions, options, and overall structure. Specifically, the questions should be relevant and specific to the given research topic and intent. The options should be tailored to the questions, ensuring they are mutually exclusive, completed, and ordered sensibly. Moreover, the sequence of questions should follow a logical order, grouping similar topics together. As a result, automatically generating questionnaires presents a significant challenge and this area has received limited attention primarily due to the scarcity of high-quality datasets. To address these issues, we present Qsnail, the first dataset specifically constructed for the questionnaire generation task, which comprises 13,168 human-written questionnaires gathered from online platforms. We further conduct experiments on Qsnail, and the results reveal that retrieval models and traditional generative models do not fully align with the given research topic and intents. Large language models, while more closely related to the research topic and intents, exhibit significant limitations in terms of diversity and specificity. Despite enhancements through the chain-of-thought prompt and finetuning, questionnaires generated by language models still fall short of human-written questionnaires. Therefore, questionnaire generation is challenging and needs to be further explored. The dataset is available at: https://***/LeiyanGithub/qsnail. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Competition on robust deep learning

引用

National Science Review 2023年第6期10卷 13-15页

作者： Yinpeng Dong Chang Liu Wenzhao Xiang Hang Su Jun Zhu Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML Center THBI Lab BNRist Center Tsinghua University Institute of Image Communication and Networks Engineering in the Department of Electronic Engineering (EE) Shanghai Jiao Tong University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Peng Cheng Laboratory Pazhou Laboratory (Huangpu)

PROBLEM In recent years,the rapid development of artificial intelligence (ai) technology,especially machine learning and deep learning, is profoundly changing human production and *** various fields,such as robotics,face recognition,autonomous driving and healthcare,ai is playing an important ***,although ai is promoting the technological revolution and industrial progress,its security risks are often *** studies have found that the wellperforming deep learning models are extremely vulnerable to adversarial examples [1-3].The adversarial examples are crafted by applying small,humanimperceptible perturbations to natural examples,but can mislead deep learning models to make wrong *** vulnerability of deep learning models to adversarial examples can raise security and safety threats to various realworld applications.

关键词： robustness adversarial example adversarial training deep learning

来源：评论

学校读者我要写书评

暂无评论

Classifier Guidance Enhances Diffusion-Based Adversarial Purification by Preserving Predictive Information 27

Classifier Guidance Enhances Diffusion-Based Adversarial Pur...

引用

27th European Conference on Artificial Intelligence, ECai 2024

作者： Zhang, Mingkun Li, Jianing Chen, Wei Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781643685489

Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods. © 2024 The Authors.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

SLANG: New Concept Comprehension of Large Language Models

SLANG: New Concept Comprehension of Large Language Models

引用

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

作者： Mei, Lingrui Liu, Shenghua Wang, Yiwei Bi, Baolong Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China University of California Los Angeles United States University of California Merced United States University of Chinese Academy of Sciences China

ISBN: (纸本)9798891761643

The dynamic nature of language, particularly evident in the realm of slang and memes on the Internet, poses serious challenges to the adaptability of Large Language Models (LLMs). Traditionally anchored to static datasets, these models often struggle to keep up with the rapid linguistic evolution characteristic of online communities. This research aims to bridge this gap by enhancing LLMs' comprehension of the evolving new concepts on the Internet, without the high cost of continual retraining. In pursuit of this goal, we introduce SLANG, a benchmark designed to autonomously integrate novel data and assess LLMs' ability to comprehend emerging concepts, alongside FOCUS, an approach uses causal inference to enhance LLMs to understand new phrases and their colloquial context. Our benchmark and approach involves understanding real-world instances of linguistic shifts, serving as contextual beacons, to form more precise and contextually relevant connections between newly emerging expressions and their meanings. The empirical analysis shows that our causal inference-based approach outperforms the baseline methods in terms of precision and relevance in the comprehension of Internet slang and memes. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Token Biaser: Knowledge Editing via Biasing key Entities

Adaptive Token Biaser: Knowledge Editing via Biasing Key Ent...

引用

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

作者： Bi, Baolong Liu, Shenghua Wang, Yiwei Mei, Lingrui Gao, Hongcheng Xu, Yilong Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China University of Chinese Academy of Sciences China University of California Los Angeles United States University of California Merced United States

ISBN: (纸本)9798891761681

The parametric knowledge memorized by large language models (LLMs) becomes outdated quickly. In-context editing (ICE) is currently the most effective method for updating the knowledge of LLMs. Recent advancements involve enhancing ICE by modifying the decoding strategy, obviating the need for altering internal model structures or adjusting external prompts. However, this enhancement operates across the entire sequence generation, encompassing a plethora of non-critical tokens. In this work, we introduce Adaptive Token Biaser (ATBIAS), a new decoding technique designed to enhance ICE. It focuses on the tokens that are mostly related to knowledge during decoding, biasing their logits by matching key entities related to new and parametric knowledge. Experimental results show that ATBIAS significantly enhances ICE performance, achieving up to a 32.3% improvement over state-of-the-art ICE methods while incurring only half the latency. ATBIAS not only improves the knowledge editing capabilities of ICE but can also be widely applied to LLMs with negligible cost. © 2024 Association for Computational Linguistics.

关键词： Ice

来源：评论

学校读者我要写书评

暂无评论

List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation 24

List-aware Reranking-Truncation Joint Model for Search and R...

引用

33rd ACM Web Conference, WWW 2024

作者： Xu, Shicheng Pang, Liang Xu, Jun Shen, Huawei Cheng, Xueqi CAS Key Laboratory of AI Security Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China CAS Key Laboratory of AI Security Institute of Computing Technology Chinese Academy of Sciences Beijing China Gaoling School of Artificial Intelligence Renmin University of China Beijing China

ISBN: (纸本)9798400701719

The results of information retrieval (IR) are usually presented in the form of a ranking list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List-aware retrieval aims to capture the list-level contextual features to return a better list, mainly including reranking and truncation. Reranking finely re-scores the documents in the list. Truncation dynamically determines the cut-off point of the ranked list to achieve the trade-off between overall relevance and avoiding misinformation from irrelevant documents. Previous studies treat them as two separate tasks and model them separately. However, the separation is not optimal. First, it is hard to share the contextual information of the ranking list between the two tasks. Second, the separate pipeline usually meets the error accumulation problem, where the small error from the reranking stage can largely affect the truncation stage. To solve these problems, we propose a Reranking-Truncation joint model (GenRT) that can perform the two tasks concurrently. GenRT integrates reranking and truncation via a generative paradigm based on an encoder-decoder architecture with novel loss functions for joint optimization to learn both tasks. Sharing parameters by the joint model is conducive to making full use of the common modeling information of the two tasks. Besides, the two tasks are performed concurrently and co-optimized to solve the error accumulation problem between separate stages. Experiments on public learning-to-rank benchmarks and open-domain Q&A tasks show that our method achieves SOTA performance on both reranking and truncation tasks for web search and retrieval-augmented LLMs. © 2024 Owner/Author.

关键词： Information retrieval

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：