•  
  •  
 

Journal of Scientific Information Research

Keywords

full-text bibliometrics, large language models, knowledge intelligence, human-AI collaboration, knowledge reasoning

Abstract

[Purpose/significance] In September 2025, the 8th Chengdu Conference on Scientometrics & Evaluation, hosted by the National Science Library (Chengdu), Chinese Academy of Sciences, and undertaken by the Scientometrics & Evaluation Research Center (SERC), was held in Chengdu. This article reviews the Academic Salon on Full-Text Bibliometric Analysis at the forum, summarizing methodological advances, application expansion, and paradigm shifts in full-text bibliometrics in the era of large language models (LLMs), and providing references for future research. [Method/process] Based on invited talks and on-site discussions, this article synthesizes the research paradigms and application directions of LLM enabled full-text bibliometrics. It highlights key viewpoints and practical approaches across topics including intelligent data annotation, fine-grained knowledge understanding, knowledge relation inference, knowledge tracing and flow analysis, scientific document understanding and automated review generation, and scientific research evaluation. [Result/conclusion] LLMs are driving full-text bibliometrics from shallow semantic analysis centered on topic terms and citation structures toward knowledge intelligence grounded in fine-grained knowledge understanding and knowledge reasoning. Information science research is undergoing notable changes in data utilization, interpretation of knowledge units, reasoning practices, explanation of bibliometric outcomes, and human-AI collaboration. Nevertheless, evaluating the reliability of LLM outputs, achieving a prospective and critical comprehension of scientific literature, and verifying the validity of bibliometric metrics are still the main challenges.

First Page

68

Last Page

77

Submission Date

26-Jan-2026

Revision Date

3-Apr-2026

Acceptance Date

23-Apr-2026

Published Date

1-Oct-2026

Reference

[1] 周海晨，章成志，徐硕，等. 知识创新视角下全文本计量分析的应用与思考：2024全文本文献计量分析学术沙龙综述[J]. 科技情报研究，2025，7（4）：82-90.

[2] THELWALL M. ChatGPT for complex text evaluation tasks[J]. Journal of the Association for Information Science & Technology，2025，76（4）：645-648.

[3] WU M，SIVERTSEN G，ZHANG L，et al. Scaling research aim identification：Language models for classifying scientific and societal-oriented studies[J]. Journal of the Association for Information Science and Technology，2025，76（11）：1470-1487.

[4] ZHANG Y，ZHANG C，KOUSHA K. Editorial：artificial intelligence for scientometrics（Part I）[J]. Scientometrics，2025，130（10，SI）：5281-5284.

[5] 卢超，章成志，王玉琢，等. 语义特征分析的深化：学术文献的全文计量分析研究综述[J]. 中国图书馆学报，2021，47（2）：110-131.

[6] 胡志刚，章成志. 悄然兴起的全文计量分析[J]. 图书馆论坛，2021，41（3）：1-11.

[7] ZHAO W X，ZHOU K，LI J，et al. A Survey of Large Language Models[J]. Frontiers of Computer Science，2026，20（12）：2012627.

[8] WEI J，WANG X，SCHUURMANS D，et al. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models[C]//Proceedings of the 36th International Conference on Neural Information Processing Systems. Red Hook，NY，USA：Curran Associates Inc.，2022：24824-24837.

[9] XU S，LI J，AN X，et al. Annotation and identification of scientific data sharing information from data availability section[C]//Proceedings of the 20th International Conference on Scientometrics and Informetrics. Yerevan：International Society for Scientometrics and Informetrics，2025：119-127.

[10] NISHIKAWA K，KOSHIBA H. Exploring the applicability of large language models to citation context analysis[J]. Scientometrics，2024，129（11）：6751-6777.

[11] ZHANG R，LI Y，MA Y，et al. LLMaAA：Making Large Language Models as Active Annotators[C]//BOUAMOR H，PINO J，BALI K. Findings of the Association for Computational Linguistics：EMNLP 2023. Singapore：Association for Computational Linguistics，2023：13088-13103.

[12] XIE Q，WALTMAN L. A comparison of citation-based clustering and topic modeling for science mapping[J]. Scientometrics，2025，130（5）：2497-2522.

[13] VAL-CALVO M，EGAÑA ARANGUREN M，MULERO-HERNÁNDEZ J，et al. OntoGenix：Leveraging large language models for enhanced ontology engineering from datasets[J]. Information Processing & Management，2025，62（3）：104042.

[14] HOU S，ZHANG S，FEI C. Rhetorical structure theory：A comprehensive review of theory，parsing methods and applications[J]. Expert Systems with Applications，2020，157：113421.

[15] SOLLACI L B，PEREIRA M G. The introduction，methods，results，and discussion（IMRAD）structure：a fifty-year survey[J]. Journal of the Medical Library Association，2004，92（3）：364-371.

[16] CAI M，YANG Z，JIAN P. Improving Implicit Discourse Relation Recognition with Semantics Confrontation[C]//CALZOLARI N，KAN M Y，HOSTE V，et al. Proceedings of the 2024 Joint International Conference on Computational Linguistics，Language Resources and Evaluation（LREC-COLING 2024）. Torino，Italia：ELRA and ICCL，2024：8828-8839.

[17] XIANG W，WANG B. A Survey of Implicit Discourse Relation Recognition[J]. ACM Computing Surveys，2023，55（12）：1-34.

[18] LU Y，HONG Y，WANG Z，et al. Enhancing Reasoning Capabilities by Instruction Learning and Chain-of-Thoughts for Implicit Discourse Relation Recognition[C]//BOUAMOR H，PINO J，BALI K. Findings of the Association for Computational Linguistics：EMNLP 2023. Singapore：Association for Computational Linguistics，2023：5634-5640.

[19] ALTMAMI N I，MENAI M E B. Automatic summarization of scientific articles：A survey[J]. Journal of King Saud University-Computer and Information Sciences，2022，34（4）：1011-1028.

[20] LIU R，MAO X L，HUANG H. DSciSum：Detailed summarization of long scientific documents[J]. Knowledge-Based Systems，2025，317：113409.

[21] YUAN H，HONG S，ZHANG H. StrucSum: graph-structured reasoning for long document extractive summarization with LLMs[C]//Findings of the Association for Computational Linguistics：EACL 2026. Rabat: Association for Computational Linguistics，2026：3708-3721.

[22] AROEIRA R I，CASTANHO M A R B. Can citation metrics predict the true impact of scientific papers?[J]. The FEBS Journal，2020，287（12）：2440-2448.

[23] HUANG H，ZHU D，WANG X. Evaluating scientific impact of publications：combining citation polarity and purpose[J]. Scientometrics，2022，127（9）：5257-5281.

[24] XUE Z，HE G，LIU J，et al. Re-examining lexical and semantic attention：Dual-view graph convolutions enhanced BERT for academic paper rating[J]. Information Processing & Management，2023，60（2）：103216.

[25] LIN C，JIAYU R，HE G，et al. Recurrent Alignment with Hard Attention for Hierarchical Text Rating[C]//Al-ONAIZAN Y，BANSAL M，CHEN Y N. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. Miami，Florida，USA：Association for Computational Linguistics，2024：18643-18657.

[26] JAHAN I，LASKAR M T R，PENG C，et al. A comprehensive evaluation of large language models on benchmark biomedical text processing tasks[J]. Computers in Biology and Medicine，2024，171：108189.

[27] BOYACK K W，ECK N J VAN，COLAVIZZA G，et al. Characterizing in-text citations in scientific articles：A large-scale analysis[J]. Journal of Informetrics，2018，12（1）：59-73.

[28] ZHANG C，LIU L，WANG Y. Characterizing references from different disciplines：A perspective of citation content analysis[J]. Journal of Informetrics，2021，15（2）：101134.

[29] ZHANG J，MAATOUK A，CHEN J，et al. LitFM：A Retrieval Augmented Structure-aware Foundation Model For Citation Graphs[C]//Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2. New York，NY，USA：Association for Computing Machinery，2025：3728-3739.

[30] LI S，HUANG J，ZHUANG J，et al. SciLitLLM: how to adapt LLMs for scientific literature understanding[C/OL]//The Thirteenth International Conference on Learning Representations. Singapore：OpenReview.net，2025[2026-08-21]. https://openreview.net/forum?id=8dzKkeWUUb.

[31] LU W，LUU R K，BUEHLER M J. Fine-tuning large language models for domain adaptation：exploration of training strategies，scaling，model merging and synergistic capabilities[J]. NPJ Computational Materials，2025，11（1）：84.

[32] ASAI A，HE J，SHAO R，et al. Synthesizing scientific literature with retrieval-augmented language models[J]. Nature，2026，650（8103）：857-863.

[33] FONSECA M，COHEN S B. Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?[C]//MARTINS A，SRIKUMAR V，KU L W. Findings of the Association for Computational Linguistics：ACL 2024. Bangkok，Thailand：Assoc Computational Linguistics-Acl，2024：8599-8618.

[34] SKARLINSKI M D，COX S，LAURENT J M，et al. Language agents achieve superhuman synthesis of scientific knowledge[J]. e-prints，arXiv：2409.13740.

[35] ADAM D. When AI rejects your grant proposal：algorithms are helping to make funding decisions[J]. Nature，2025，645（8082）：832-833.

[36] HUANG S，LU W，XU Z，et al. Identifying potentially disruptive research via a comparative power-based large model[J]. Information Processing & Management，2025，62（6）：104207.

[37] BARLÖSIUS E. Concepts of Originality in the Natural Science，Medical，and Engineering Disciplines：An Analysis of Research Proposals[J]. Science，Technology，& Human Values，2019，44（6）：915-937.

[38] DIRK L. A Measure of Originality：The Elements of Science[J]. Social Studies of Science，1999，29（5）：765-776.

[39] GUETZKOW J，LAMONT M，MALLARD G. What is Originality in the Humanities and the Social Sciences?[J]. American Sociological Review，2004，69（2）：190-212.

[40] SHIBAYAMA S，WU Z，YIN D，et al. State of the art of novelty indicators[EB/OL].（2025-10-23）[2026-08-21]. https://doi.org/10.2139/ssrn.5648547.

Digital Object Identifier (DOI)

10.19809/j.cnki.kjqbyj.2026.04.007

Download

Share

COinS