检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Haoran Lin, Xiaoli Hu, Jing Zhang, Xiaolong Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan China

ISBN: (纸本)9798350386226

This paper describes a multi target drug design method based on features of the target proteins. The multi target drug which inhibit multiple proteins have prospective applications, but design is difficult. In this study, the target protein sequences are embedded to obtain target features. The features of each target are independently encoded as target latent vectors, and the features of multiple targets are jointly encoded as target similarity latent vectors. Based on the features of targets and the similarity features among the targets, multi target drugs are efficiently designed. In the experiments, the designed multi target drugs can be docked with target proteins with a proprietary molecular structure according to the requirements of different target pocket structures. The excellent fitness among the molecular structure of multi target drugs and the protein structure of multiple targets confirms the performance of the proposed method. In the molecular docking part of the experi¬ments, the binding affinity of designed multi target drugs is far better than that in the previous studies, which administrates the better performance of this work. © 2024 IEEE.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents 38

Watch Out for Your Agents! Investigating Backdoor Threats to...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Yang, Wenkai Bi, Xiaohan Lin, Yankai Chen, Sishuo Zhou, Jie Sun, Xu Gaoling School of Artificial Intelligence Renmin University of China Beijing China Center for Data Science Peking University China Pattern Recognition Center WeChat AI Tencent Inc. China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China

Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and security of LLM-based agents during applications. However, the safety issues of LLM-based agents are currently under-explored. In this work, we take the first step to investigate one of the typical safety threats, backdoor attack, to LLM-based agents. We first formulate a general framework of agent backdoor attacks, then we present a thorough analysis of different forms of agent backdoor attacks. Specifically, compared with traditional backdoor attacks on LLMs that are only able to manipulate the user inputs and model outputs, agent backdoor attacks exhibit more diverse and covert forms: (1) From the perspective of the final attacking outcomes, the agent backdoor attacker can not only choose to manipulate the final output distribution, but also introduce the malicious behavior in an intermediate reasoning step only, while keeping the final output correct. (2) Furthermore, the former category can be divided into two subcategories based on trigger locations, in which the backdoor trigger can either be hidden in the user query or appear in an intermediate observation returned by the external environment. We implement the above variations of agent backdoor attacks on two typical agent tasks including web shopping and tool utilization. Extensive experiments show that LLM-based agents suffer severely from backdoor attacks and such backdoor vulnerability cannot be easily mitigated by current textual backdoor defense algorithms. This indicates an urgent need for further research on the development of targeted defenses against backdoor attacks on LLM-based agents. © 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

Cross-GAN: Unsupervised Image-to-Image Translation 6

Cross-GAN: Unsupervised Image-to-Image Translation

引用

6th IEEE information Technology and Mechatronics Engineering Conference, ITOEC 2022

作者： Peng, Xu Li, Qishen Wu, Taida Yuan, Sihao Nanchang Hangkong University School of Information Engineering Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Jiangxi Nanchang China

ISBN: (纸本)9781665431859

In recent years, unsupervised image-to-image translation is a topic in computer graphics. This paper proposes a new architecture to translate the image through the idea of sharing and decoupling, termed as Cross-GAN, which can better extract the style in the process of translation, and does not change the original outline and background. We improve the cycle consistency loss and reconstruction loss for the unique properties of the model to make the image more realistic. Because GAN[1] only generates the target style image by inputting the content image, and the information of the target domain image is not used in the training process. We input style images and content images through cross-input. The style images play a guiding role in the generator, and the effect of image are better by fusing style features and content features. Due to the fact that the image of the target domain is input, it is easy to produce the phenomenon of over-fitting. In order to prevent over-fitting training, we improve the cycle consistency loss and reuse the input encoder to make the model more compact. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning

RoTBench: A Multi-Level Benchmark for Evaluating the Robustn...

引用

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

作者： Ye, Junjie Wu, Yilong Gao, Songyang Huang, Caishuang Li, Sixian Li, Guanyu Fan, Xiaoran Zhang, Qi Gui, Tao Huang, Xuanjing School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

ISBN: (纸本)9798891761643

Tool learning has generated widespread interest as a vital means of interaction between Large Language Models (LLMs) and the physical world. Current research predominantly emphasizes LLMs' capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world. To bridge this gap, we introduce RoTBench, a multi-level benchmark for evaluating the robustness of LLMs in tool learning. Specifically, we establish five external environments, each featuring varying levels of noise (i.e., Clean, Slight, Medium, Heavy, and Union), providing an in-depth analysis of the model's resilience across three critical phases: tool selection, parameter identification, and content filling. Experiments involving six widely-used models underscore the urgent necessity for enhancing the robustness of LLMs in tool learning. For instance, the performance of GPT-4 even drops significantly from 80.00 to 58.10 when there is no substantial change in manual accuracy. More surprisingly, the noise correction capability inherent in the GPT family paradoxically impedes its adaptability in the face of mild noise. In light of these findings, we propose RoTTuning, a strategy that enriches the diversity of training environments to bolster the robustness of LLMs in tool learning. The code and data are available at https://***/Junjie-Ye/RoTBench. © 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

PDF-to-Tree: Parsing PDF Text Blocks into a Tree

PDF-to-Tree: Parsing PDF Text Blocks into a Tree

引用

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

作者： Zhang, Yue Zhang, Zhihao Lai, Wenbin Zhang, Chong Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

ISBN: (纸本)9798891761681

In many PDF documents, the reading order of text blocks is missing, which can hinder machine understanding of the document's content. Existing works try to extract one universal reading order for a PDF file. However, applications, like Retrieval Augmented Generation (RAG), require breaking long articles into sections, subsections and table cells for better indexing. For this reason, this paper introduces a new task and dataset, PDF-to-Tree, which organizes the text blocks of a PDF into a tree structure. Since a PDF may contain thousands of text blocks, this paper proposes a transition-based parser that uses a greedy strategy to build the tree structure. Compared to the parser for plain text, we also use multi-modal features to encode the parser state. Experiments show that our approach achieves an accuracy of 93.93%, surpassing the performance of baseline methods by an improvement of 6.72%. The dataset is public available at https://***/yuezh000/PDFto-Tree. © 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

Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning

Improving Discriminative Capability of Reward Models in RLHF...

引用

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

作者： Chen, Lu Zheng, Rui Wang, Binghai Jin, Senjie Huang, Caishuang Ye, Junjie Zhang, Zhihao Zhou, Yuhao Xi, Zhiheng Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9798891761643

Reinforcement Learning from Human Feedback (RLHF) is a crucial approach to aligning language models with human values and intentions. A fundamental challenge in this method lies in ensuring that the reward model accurately understands and evaluates human preferences. Current methods rely on ranking losses to teach the reward model to assess preferences, but they are susceptible to noise and ambiguous data, often failing to deeply understand human intentions. To address this issue, we introduce contrastive learning into the reward modeling process. In addition to supervised ranking loss, we introduce an unsupervised contrastive loss to enable the reward model to fully capture the distinctions in contrastive data. Experimental results demonstrate that the proposed contrastive learning-based reward modeling method effectively enhances the generalization of the reward model, stabilizes the reinforcement learning training process, and improves the final alignment with human preferences. © 2024 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities

TransferTOD: A Generalizable Chinese Multi-Domain Task-Orien...

引用

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

作者： Zhang, Ming Huang, Caishuang Wu, Yilong Liu, Shichun Zheng, Huiyuan Dong, Yurui Shen, Yujiong Dou, Shihan Zhao, Jun Ye, Junjie Zhang, Qi Gui, Tao Huang, Xuanjing School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Institute of Modern Languages and Linguistics Fudan University China

ISBN: (纸本)9798891761643

Task-oriented dialogue (TOD) systems aim to efficiently handle task-oriented conversations, including information collection. How to utilize TOD accurately, efficiently and effectively for information collection has always been a critical and challenging task. Recent studies have demonstrated that Large Language Models (LLMs) excel in dialogue, instruction generation, and reasoning, and can significantly enhance the performance of TOD through fine-tuning. However, current datasets primarily cater to user-led systems and are limited to predefined specific scenarios and slots, thereby necessitating improvements in the proactiveness, diversity, and capabilities of TOD. In this study, we present a detailed multi-domain task-oriented data construction process for conversations, and a Chinese dialogue dataset generated based on this process, TransferTOD, which authentically simulates human-computer dialogues in 30 popular life service scenarios. Leveraging this dataset, we trained a model using full-parameter fine-tuning called TransferTOD-7B, showcasing notable abilities in slot filling and questioning. Our work has demonstrated its strong generalization capabilities in various downstream scenarios, significantly enhancing both data utilization efficiency and system performance. The data is released in https://***/KongLongGeFDU/TransferTOD. © 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

LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration

LONGAGENT: Achieving Question Answering for 128k-Token-Long ...

引用

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

作者： Zhao, Jun Zu, Can Xu, Hao Lu, Yi He, Wei Ding, Yiwen Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Institute of Modern Languages and Linguistics Fudan University China

ISBN: (纸本)9798891761643

Large language models (LLMs) have achieved tremendous success in understanding language and processing text. However, question-answering (QA) on lengthy documents faces challenges of resource constraints and a high propensity for errors, even for the most advanced models such as GPT-4 and Claude2. In this paper, we introduce LONGAGENT, a multi-agent collaboration method that enables efficient and effective QA over 128k-token-long documents. LONGAGENT adopts a divide- and-conquer strategy, breaking down lengthy documents into shorter, more manageable text chunks. A leader agent comprehends the user's query and organizes the member agents to read their assigned chunks, reasoning a final answer through multiple rounds of discussion. Due to members' hallucinations, it's difficult to guarantee that every response provided by each member is accurate. To address this, we develop an inter-member communication mechanism that facilitates information sharing, allowing for the detection and mitigation of hallucinatory responses. Experimental results show that a LLaMA-2 7B driven by LONGAGENT can effectively support QA over 128k-token documents, achieving 16.42% and 1.63% accuracy gains over GPT-4 on single-hop and multi-hop QA settings, respectively. © 2024 Association for Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation

Inference-Time Decontamination: Reusing Leaked Benchmarks fo...

引用

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

作者： Zhu, Qin Cheng, Qinyuan Peng, Runyu Li, Xiaonan Liu, Tengxiao Peng, Ru Qiu, Xipeng Huang, Xuanjing School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China College of Computer Science and Technology Zhejiang University China

ISBN: (纸本)9798891761681

The training process of large language models (LLMs) often involves varying degrees of test data contamination (Yang et al., 2023b).Although current LLMs are achieving increasingly better performance on various benchmarks, their performance in practical applications does not always match their benchmark *** of benchmarks can prevent the accurate assessment of LLMs' true ***, constructing new benchmarks is costly, labor-intensive and still carries the risk of ***, in this paper, we ask the question "Can we reuse these leaked benchmarks for LLM evaluation?" We propose Inference-Time Decontamination (ITD) to address this issue by detecting and rewriting leaked samples without altering their *** can mitigate performance inflation caused by memorizing leaked *** proof-of-concept experiments demonstrate that ITD reduces inflated accuracy by 22.9% on GSM8K and 19.0% on *** MMLU, using Inference-time Decontamination can lead to a decrease in the results of Phi3 and Mistral by 6.7% and 3.6% *** hope that ITD can provide more truthful evaluation results for large language models. © 2024 Association for Computational Linguistics.

关键词： Decontamination

来源：评论

学校读者我要写书评

暂无评论

A research on cross-chain and interoperation methods of fusion protocol

IET Blockchain

引用

IET Blockchain 2024年第1期4卷 18-29页

作者： Ming, Li Wenpeng, Song Ankai, Li Ziming, Zhou Mianchen, Liu Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of Blockchain Shanghai China China Electronics Standardization Institute Beijing China School of Economics and Management Beihang University Beijing China Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations Beijing China

At present, cross-chain technology and cross-chain system pay more attention to cross-chain security and performance, and have shown great improvement in security, scalability and efficiency. However, the generality of cross-chain technology in different scenarios is poor, and it may not fit in different business fields. In order to solve the generality problem of cross-chain technology, this paper sorts out and analyzes the research of blockchain cross-chain protocol, and proposes a fusion protocol cross-chain method based on relay-chain technology. This paper will introduce the cross-chain framework and cross-chain transaction process of fusion protocol. Cross-chain framework includes blockchain cross-chain interaction architecture, cross-chain interaction governance mechanism and cross-chain privacy protection scheme. The transaction process is divided into three different stages. Finally, combined with cross-chain key technologies and landing application requirements, the future research direction of blockchain cross-chain technology is given. The fusion protocol cross-chain method based on relay-chain technology proposed here is a groundbreaking innovation in the field of blockchain cross-chain technology. By integrating the advantages of different blockchain systems and protocols, the fusion protocol is able to achieve a high degree of generality and compatibility, making it suitable for various business scenarios and applications. © 2023 The Authors. IET Blockchain published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

关键词： Blockchain

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：