检索结果-内蒙古大学图书馆

Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Haotian Chen, Bingsheng Zhou, Xiangdong School of Computer Science Fudan University Shanghai Key Laboratory of Data Science China

Document-level relation extraction (DocRE) attracts more research interest recently. While models achieve consistent performance gains in DocRE, their underlying decision rules are still understudied: Do they make the right predictions according to rationales? In this paper, we take the first step toward answering this question and then introduce a new perspective on comprehensively evaluating a model. Specifically, we first conduct annotations to provide the rationales considered by humans in DocRE. Then, we conduct investigations and reveal the fact that: In contrast to humans, the representative state-of-the-art (SOTA) models in DocRE exhibit different decision rules. Through our proposed RE-specific attacks, we next demonstrate that the significant discrepancy in decision rules between models and humans severely damages the robustness of models and renders them inapplicable to real-world RE scenarios. After that, we introduce mean average precision (MAP) to evaluate the understanding and reasoning capabilities of models. According to the extensive experimental results, we finally appeal to future work to consider evaluating both performance and the understanding ability of models for the development of their applications. We make our annotations and code publicly available © 2023, CC BY.

关键词： Extraction

Generating Variable Explanations via Zero-shot Prompt Learning

学校读者我要写书评

暂无评论

Generating Variable Explanations via Zero-shot Prompt Learni...

IEEE International Conference on Automated Software Engineering (ASE)

作者： Chong Wang Yiling Lou Junwei Liu Xin Peng Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China

As basic elements in program, variables convey essential information that is critical for program comprehension and maintenance. However, understanding the meanings of variables in program is not always easy for developers, since poor-quality variable names are prevalent while such variable are less informative for program comprehension. Therefore, in this paper, we target at generating concise natural language explanations for variables to facilitate program comprehension. In particular, there are two challenges in variable explanation generation, including the lack of training data and the association with complex code contexts around the variable. To address these issues, we propose a novel approach ZeroVar,which leverages code pre-trained models and zero-shot prompt learning to generate explanations for the variable based on its code context. ZeroVarcontains two stages: (i) a pre-training stage that continually pre-trains a base model (i.e., CodeT5) to recover the randomly-masked parameter descriptions in method docstrings; and (ii) a zero-shot prompt learning stage that leverages the pre-trained model to generate explanations for a given variable via the prompt constructed with the variable and its belonging method context. We then extensively evaluate the quality and usefulness of the variable explanations generated by *** construct an evaluation dataset of 773 variables and their reference explanations. Our results show that ZeroVarcan generate higher-quality explanations than baselines, not only on automated metrics such as BLEU and ROUGE, but also on human metrics such as correctness, completeness, and conciseness. Moreover, we further assess the usefulness of ZeroVAR-generated explanations on two downstream tasks related to variable naming quality, i.e., abbreviation expansion and spelling correction. For abbreviation expansion, the generated variable explanations can help improve the present rate (+13.1%), precision (+3.6%), and recall (+10.0%) of

关键词：

Recommending Analogical APIs via Knowledge Graph Embedding

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Mingwei Yang, Yanjun Lou, Yiling Peng, Xin Zhou, Zhong Du, Xueying Yang, Tianyong The School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China

Library migration, which replaces the current library with a different one to retain the same software behavior, is common in software evolution. An essential part of this is finding an analogous API for the desired functionality. However, due to the multitude of libraries/APIs, manually finding such an API is time-consuming and error-prone. Researchers created automated analogical API recommendation techniques, notably documentation-based methods. Despite potential, these methods have limitations, e.g., incomplete semantic understanding in documentation and scalability issues. In this study, we present KGE4AR, a novel documentation-based approach using knowledge graph (KG) embedding for recommending analogical APIs during library migration. KGE4AR introduces a unified API KG to comprehensively represent documentation knowledge, capturing high-level semantics. It further embeds this unified API KG into vectors for efficient, scalable similarity calculation. We assess KGE4AR with 35,773 Java libraries in two scenarios, with and without target libraries. KGE4AR notably outperforms state-of-the-art techniques (e.g., 47.1%-143.0% and 11.7%-80.6% MRR improvements), showcasing scalability with growing library counts. © 2023, CC BY.

关键词： Knowledge graph

Motion Matters: Difference-based Multi-scale Learning for Infrared UAV Detection

学校读者我要写书评

暂无评论

Motion Matters: Difference-based Multi-scale Learning for In...

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： He, Ruian Zhou, Shili Cheng, Ri Sun, Yuqi Tan, Weimin Yan, Bo Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (纸本)9798350302493

Unmanned Aerial Vehicle (UAV) detection in the wild is a challenging task due to the presence of background noise and the varying size of the object. To address these obstacles, we propose a novel learning framework for robust UAV detectors, which we call Difference-based Multi-scale Learning (DML). We argue that motion information matters in UAV detection because of the low recognition in one frame. Our method utilizes the frame difference of multiple previous frames, extracting motion information and blocking background noise. We also fuse multiple spatial-temporal scales for training and inferencing, enabling fusion from different sources. In addition, to better evaluate the performance of UAV detection in different scales, we propose Multi-Scale Average Precision (MSAP) metric to aggregate the detection accuracy over multiple scales. Through extensive experiments, we demonstrate that our proposed approach improves the detection accuracy of baseline models. Notably, we achieve SOTA performance in the 3rd Anti-UAV Challenge, with 2nd place in Track 2 and 4th place in Track 1. © 2023 IEEE.

关键词： Antennas

MultiLingPoT: Enhancing Mathematical Reasoning with Multilingual Program Fine-tuning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Nianqi Liang, Zujie Yuan, Siyu Liang, Jiaqing Wei, Feng Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China MYbank Ant Group China School of Data Science Fudan University China

Program-of-Thought (PoT), which aims to use programming language instead of natural language as an intermediate step in reasoning, is an important way for LLMs to solve mathematical problems. Since different programming languages excel in different areas, it is natural to use the most suitable language for solving specific problems. However, current PoT research only focuses on single language PoT, ignoring the differences between different programming languages. Therefore, this paper proposes an multilingual program reasoning method, MultiLingPoT. This method allows the model to answer questions using multiple programming languages by fine-tuning on multilingual data. Additionally, prior and posterior hybrid methods are used to help the model select the most suitable language for each problem. Our experimental results show that the training of MultiLingPoT improves each program’s mathematical reasoning by about 2.5%. Moreover, with proper mixing, the performance of MultiLingPoT can be further improved, achieving a 6% increase compared to the single-language PoT © 2024, CC BY-NC-SA.

关键词： Ada (programming language)

Small Language Model Can Self-Correct

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Han, Haixia Liang, Jiaqing Shi, Jie He, Qianyu Xiao, Yanghua Shanghai Institute of AI for Education School of Computer Science and Technology East China Normal University China School of Data Science Fudan University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China

Generative Language Models (LMs) such as ChatGPT have exhibited remarkable performance across various downstream tasks. Nevertheless, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone. Previous studies have devised sophisticated pipelines and prompts to induce large LMs to exhibit the capability for self-correction. However, large LMs are explicitly prompted to verify and modify their answers separately rather than completing all steps spontaneously like humans. Moreover, these complex prompts are extremely challenging for small LMs to follow. In this paper, we introduce the Intrinsic Self-Correction (ISC) in generative language models, aiming to correct the initial output of LMs in a self-triggered manner, even for those small LMs with 6 billion parameters. Specifically, we devise a pipeline for constructing self-correction data and propose Partial Answer Masking (PAM), aiming to endow the model with the capability for intrinsic self-correction through fine-tuning. We conduct experiments using LMs with parameters sizes ranging from 6 billion to 13 billion in two tasks, including commonsense reasoning and factual knowledge reasoning. Our experiments demonstrate that the outputs generated using ISC outperform those generated without self-correction. We believe that the output quality of even small LMs can be further improved by empowering them with the ability to intrinsic self-correct. Copyright © 2024, The Authors. All rights reserved.

关键词： Pipelines

DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Aili Du, Chengyu Chen, Jiangjie Xu, Jinghan Zhang, Yikai Yuan, Siyu Chen, Zulong Li, Liangyue Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China ByteDance Inc China School of Data Science Fudan University China Alibaba Group China

To advance personalized applications such as recommendation systems and user behavior prediction, recent research increasingly adopts large language models (LLMs) for human-readable persona modeling. In dynamic real-world scenarios, effective persona modeling necessitates leveraging streaming behavior data to continually optimize user personas. However, existing methods—whether regenerating personas or incrementally extending them with new behaviors—often fail to achieve sustained improvements in persona quality or future behavior prediction accuracy. To address this, we propose DEEPER, a novel approach for dynamic persona modeling that enables continual persona optimization. Specifically, we enhance the model’s direction-search capability through an iterative reinforcement learning framework, allowing it to automatically identify effective update directions and optimize personas using discrepancies between user behaviors and model predictions. Extensive experiments on dynamic persona modeling involving 4,800 users across 10 domains highlight DEEPER’s superior persona optimization capabilities, delivering an impressive 32.2% average reduction in user behavior prediction error over four update rounds—outperforming the best baseline by a remarkable 22.92%.1 Copyright © 2025, The Authors. All rights reserved.

关键词： Digital elevation model

Generation of tunable superchiral spot in metal-insulator-metal waveguide

学校读者我要写书评

暂无评论

Chinese Optics Letters 2023年第1期21卷 125-130页

作者：庄涛胡海峰詹其文 School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China Zhangjiang Laboratory Shanghai 201204China Shanghai Key Laboratory of Modern Optical System University of Shanghai for Science and TechnologyShanghai 200093China

The chiral feature of an optical field can be evaluated by the parameter of g-factor enhancement,which is helpful to enhance chiroptic signals from a chiral *** this work,the superchiral spot has been theoretically proposed in metal-insulator-metal *** g-factor enhancement of the superchiral spot can be enhanced by 67-fold more than that of circularly polarized light,and the spot is confined in the deep wavelength scale along each spatial ***,the position of the superchiral spot can be tuned by manipulating the incident *** tunable superchiral spot may find applications in chiral imaging and sensing.

关键词： circular dichroism superchiral spot radially polarized beam metal-insulator-metal waveguide

Ordering Results on Largest Order Statistics from Multiple-Outlier Gamma Variables

学校读者我要写书评

暂无评论

Communications in Mathematics and Statistics 2023年第2期11卷 257-282页

作者： Yiying Zhang Yanni Hu Peng Zhao School of Statistics and Data Science LPMC and KLMDASRNankai UniversityTianjin 300071People’s Republic of China SpeakIn Technologies Co. Ltd.Shanghai 200000People’s Republic of China School of Mathematics and Statistics and RIMS Jiangsu Provincial Key Laboratory of Educational Big Data Science and EngineeringJiangsu Normal UniversityXuzhou 221116People’s Republic of China

In this article,we carry out stochastic comparisons on the maximum order statistics arising from two batches of multiple-outlier gamma random variables with different shape and scale *** is proved that,under certain conditions,the majorization order between the vectors of shape parameters together with the weak majorization order[p-larger order]between the vectors of scale parameters implies the likelihood ratio order[hazard rate order]between the largest order *** results established here strengthen and generalize some known ones in the literature.

关键词： Gamma distribution Stochastic orders Largest order statistics Majorization p-Larger order