# Ontology-Guided Multi-Agent Extraction of Evaluation Objects from Academic Review Texts: Evidence from Chinese Library and Information Science

arXiv: https://arxiv.org/abs/2608.29526 · HTML: https://mlsanity.com/paper/2608.29526/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 44 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts](https://mlsanity.com/paper/2205.01833/) (2022)
- [SciREX: A Challenge Dataset for Document-Level Information Extraction](https://mlsanity.com/paper/2005.00512/) (2020)
- [CrossNER: Evaluating Cross-Domain Named Entity Recognition](https://mlsanity.com/paper/2012.04373/) (2020)
- [Co-word Maps and Topic Modeling: A Comparison Using Small and Medium-Sized Corpora (n < 1000)](https://mlsanity.com/paper/1511.03020/) (2015)
- [Does the use of open, non-anonymous peer review in scholarly publishing introduce bias? Evidence from the F1000 post-publication open peer review publishing model](https://mlsanity.com/paper/1911.03379/) (2019)
- [Professional and Citizen Bibliometrics: Complementarities and ambivalences in the development and use of indicators](https://mlsanity.com/paper/1609.04793/) (2016)

## Abstract (arXiv)

Academic reviews, scholarly commentaries, and book reviews serve as sources of evaluative statements about theories, methods, literature, institutions, and policies, providing valuable evidence for scholarly evaluation. Existing scientific entity extraction methods mainly target research articles and are less effective for evaluation objects, which are often abstract, context-dependent, and characterized by ambiguous type boundaries. This study proposes an ontology-guided multi-agent framework for evaluation object extraction. The framework combines candidate discovery, ontology-constrained classification, and domain review. Experimental results show that it achieves a Precision of 90.33%, Recall of 84.55%, Entity-level F1 of 87.34%, Strict Typed F1 of 79.78%, and Type Accuracy of 91.35%, substantially outperforming rule-based and zero-shot baselines. Ablation results indicate that the multi-agent workflow improves recall and stability, while ontology-based boundary constraints enhance fine-grained classification and reduce category confusion. The framework supports the structured utilization of evaluative scholarly texts and provides methodological support for evidence-based research evaluation and STI mining.