Large language models (LLMs) have emerged as a potential solution to automate the complex processes involved in writing literature reviews, such as literature collection, organization, and summarization.However, it is yet unclear how good LLMs are at automating comprehensive and reliable literature reviews.This study introduces a framework to automatically evaluate the performance of LLMs in three key tasks of literature review writing: reference generation, abstract writing, and literature review composition.We introduce multidimensional evaluation metrics that assess the hallucination rates in generated references and measure the semantic coverage and factual consistency of the literature summaries and compositions against human-written counterparts.The experimental results reveal that even the most advanced models still generate hallucinated references, despite recent progress.Moreover, we observe that the performance of different models varies across disciplines when it comes to writing literature reviews.These findings highlight the need for further research and development to improve the reliability of LLMs in automating academic literature reviews.The dataset and code used in this study are publicly available in our GitHub repository 1 .

Natural Language Processing (NLP) plays a pivotal role in the realm of Digital Humanities (DH) and serves as the cornerstone for advancing the structural analysis of historical and cultural heritage texts. This is particularly true for the domains of named entity recognition (NER) and relation extraction (RE). In our commitment to expediting ancient history and culture, we present the “Chinese Historical Information Extraction Corpus”(CHisIEC). CHisIEC is a meticulously curated dataset designed to develop and evaluate NER and RE tasks, offering a resource to facilitate research in the field. Spanning a remarkable historical timeline encompassing data from 13 dynasties spanning over 1830 years, CHisIEC epitomizes the extensive temporal range and text heterogeneity inherent in Chinese historical documents. The dataset encompasses four distinct entity types and twelve relation types, resulting in a meticulously labeled dataset comprising 14,194 entities and 8,609 relations. To establish the robustness and versatility of our dataset, we have undertaken comprehensive experimentation involving models of various sizes and paradigms. Additionally, we have evaluated the capabilities of Large Language Models (LLMs) in the context of tasks related to ancient Chinese history. The dataset and code are available at https://github.com/tangxuemei1995/CHisIEC.

The evolution of language follows the rule of gradual change.Grammar, vocabulary, and lexical semantic shifts take place over time, resulting in a diachronic linguistic gap.As such, a considerable amount of texts are written in languages of different eras, which creates obstacles for natural language processing tasks, such as word segmentation and machine translation.Although the Chinese language has a long history, previous Chinese natural language processing research has primarily focused on tasks within a specific era.Therefore, we propose a cross-era learning framework for Chinese word segmentation (CWS), CROSSWISE, which uses the Switch-memory (SM) module to incorporate era-specific linguistic knowledge.Experiments on four corpora from different eras show that the performance of each corpus significantly improves.Further analyses also demonstrate that the SM can effectively integrate the knowledge of the eras into the neural network.

With the development of society, the structural steelwork tends to be larger in scale and more complicated in system. The increasing difficulties in construction ask for higher efficiency and security. Traditional 2D drawings can hardly satisfy the requirement of structural instructions, for example, the construction of boiler steel frame. This article focuses on the imperfections of 2D drawings in expressing 3D images. In order to reduce the pressures of reading drawings and dimensional analysis on engineering staffs, the use of CATIA to build 3D models by 2D drawings with the given information is suggested. Meanwhile, according to statistical methods of project management, a system managing engineering part is designed. Through the application of 3D modeling, the overall situation of the engineering structure can be known, and parts lofting and erection outfitting can be avoided. The statistical management over elements is also realized. The research focuses on the case of the boiler steel-frame owned by a thermal power plant in Hubei. 3D model is constructed by using information of 2D drawings to calculate the required mechanical equipment, human recourse and materials concerned with the project. It managed to shorten the project preparation time by one month, reduce the construction difficulties and ensure that the requirements on equipment, human recourse and materials are all satisfied.

In some mechanical transmission structures, the conjugate cam mechanism is used widely. The previous design method is not only tedious, but the substantial design is not strong, difficult to form a simulation animation, and inconvenient for subsequent analysis. The equations of conjugate cams curves are derived by the analytical method. Taking the conjugate cam in beating-up mechanism as an example, three-dimensional parametric design is implemented with Pro/Engineer secondary development. And then the after design model is imported into ADAMS to do simulation. Such an approach not only makes the design of analytical method become much simple but also makes the subsequent analyses become even more intuitive, as well as, increasing design efficiency and quality, shortening the development cycle. It has some practical value in practice.