SymTax: Symbiotic Relationship and Taxonomy Fusion for Effective Citation Recommendation

Challenge:	Existing recommendations focus on local context or global context but fail to consider actual human citation behaviour.
Approach:	They propose a recommendation architecture that considers both local and global contexts . they use hyperbolic separation to compute query-candidate similarity .
Outcome:	The proposed framework performs better on a large dataset with 8.27 million citation contexts . it learns to embed the infused taxonomies in the hyperbolic space and computes similarity .

Similar Papers

Overview

Challenge

Approach

Outcome

Dynamic Context Extraction for Citation Classification (2022.aacl-main)

Copied to clipboard

Suchetha Nambanoor Kunnath, David Pride, Petr Knoth

Information Extraction & Text Mining

Challenge:	Prior studies have focused on the application of fixed-size contiguous citation contexts or manually curated citation contextual contexts.
Approach:	They propose an automated unsupervised approach for the selection of a dynamic-size and potentially non-contiguous citation context based on transformer-based document representations and embedding similarities.
Outcome:	The proposed model improves on the domain-specific and multi-disciplinary datasets, irrespective of the dataset's domain.

LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media (2025.findings-acl)

Copied to clipboard

Haiqi Zhang, Zhengyuan Zhu, Zeyu Zhang, Chengkai Li

Semantic Text Processing

Challenge:	Social media's global reach and ease of use have transformed how millions of users exchange opinions, news, and factual claims in real-time, making it fertile ground for misinformation.
Approach:	They propose a framework that leverages large language models to construct taxonomies of factual claims from social media by generating topics at multiple levels of granularity.
Outcome:	The proposed framework produces clear, coherent, and comprehensive taxonomies on three diverse datasets and outperforms other frameworks in most metrics.

Structural Scaffolds for Citation Intent Classification in Scientific Publications (N19-1)

Copied to clipboard

Arman Cohan, Waleed Ammar, Madeleine van Zuylen, Field Cady

Information Retrieval

Challenge:	Existing methods for identifying intent of citations are limited by external linguistic resources and hand-engineered features.
Approach:	They propose a multitask model to incorporate structural information of scientific papers into citations for effective classification of citation intents.
Outcome:	The proposed model achieves a 13.3% increase in F1 score on an existing ACL anthology dataset without external linguistic resources or hand-engineered features as done in existing methods.

CiteLab: Developing and Diagnosing LLM Citation Generation Workflows via the Human-LLM Interaction (2025.acl-demo)

Copied to clipboard

Jiajun Shen, Tong Zhou, Yubo Chen, Kang Liu, Jun Zhao

Challenge:	Existing frameworks for enabling Large Language Models to generate citations are lacking . however, they can still produce hallucinated responses that are non-factual or irrelevant to the input.
Approach:	They propose an open-source and modular framework for enabling LLMs to generate citations in Question-Answering tasks.
Outcome:	The proposed framework is extensible and paired with a visual interface, Citefix, facilitating case study and modification of existing citation generation methods.

CiteBART: Learning to Generate Citations for Local Citation Recommendation (2025.emnlp-main)

Copied to clipboard

Ege Yiğit Çelik, Selma Tekir

Language Models

Challenge:	Local citation recommendation (LCR) suggests a set of papers for a citation placeholder in a given context.
Approach:	They introduce a citation-specific pre-training framework where author-date citation tokens are masked to learn to reconstruct them to fulfill local citation recommendation (LCR).
Outcome:	The proposed model achieves state-of-the-art performance on LCR benchmarks except for the FullTextPeerRead dataset, which is quite small to see the advantage of generative pre-training.

A supervised approach to taxonomy extraction using word embeddings (L18-1)

Copied to clipboard

Rajdeep Sarkar, John P. McCrae, Paul Buitelaar

Semantic Text Processing

Challenge:	a recent evaluation of a method for organizing texts into a hierarchy showed that it did not outperform a baseline.
Approach:	They propose a method that uses supervised learning to combine multiple features with a support vector machine classifier including the baseline features.
Outcome:	The proposed method outperforms the baseline method and provides stronger method for identifying taxonomic relations than previous methods.

Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering (2025.emnlp-main)

Copied to clipboard

Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Text Clustering

Challenge:	Existing taxonomy construction methods lack coherence and granularity . Existing approaches rely on manual or narrowly defined schemes .
Approach:	They propose a context-aware hierarchical taxonomy generation framework that integrates LLMs with dynamic clustering.
Outcome:	The proposed method outperforms existing methods in taxonomy coherence, granularity, and interpretability.

TEMP: Taxonomy Expansion with Dynamic Margin Loss through Taxonomy-Paths (2021.emnlp-main)

Copied to clipboard

Zichen Liu, Hongyuan Xu, Yanlong Wen, Ning Jiang, HaiYing Wu, Xiaojie Yuan

Semantic Text Processing

Challenge:	Existing taxonomies are unable to maintain coverage due to the rising of new concepts . TEMP uses pre-trained contextual encoders to predict the position of new ideas .
Approach:	They propose a self-supervised taxonomy expansion method that ranks taxonomies by ranking them . they use pre-trained contextual encoders to train the model with dynamic margin loss .
Outcome:	The proposed method outperforms state-of-the-art taxonomy expansion methods by 14.3% and 15.8% on public benchmarks.

CluHTM - Semantic Hierarchical Topic Modeling based on CluWords (2020.acl-main)

Copied to clipboard

Felipe Viegas, Washington Cunha, Christian Gomes, Antônio Pereira, Leonardo Rocha, Marcos Goncalves

Information Extraction & Text Mining

Challenge:	Hierarchical Topic modeling (HTM) exploits latent topics and relationships among them as a powerful tool for data analysis and exploration.
Approach:	They propose a hierarchical matrix factorization that exploits latent topics and relationships among them to create a powerful tool for data analysis and exploration.
Outcome:	The proposed method outperforms baselines and datasets in the vast majority of cases.

Not All Citations Are Equal:Entropy-Guided Citation Selection for Noise-Resistant Medical LLM (2026.findings-acl)

Copied to clipboard

Minyu Gao, Hanlin Xiao, Ruoyu Wang, Shuai Yang, YeXuan Zhang, Xin Wu, Xingyu Liu

Semantic Text Processing

Challenge:	Large language models have demonstrated extensive potential in medical applications . however, their practical deployment in healthcare faces significant challenges .
Approach:	They propose a training-free multi-turn reasoning framework and a post-training methodology that provides external knowledge support for large language models.
Outcome:	The proposed framework elicits internal thought, external thought, and fusion thought, with an entropy-based reward that encourages selective citation of beneficial external knowledge while penalizing noisy citations.