# Towards Automatic Evolution Tree Generation from Citation Graphs

arXiv: https://arxiv.org/abs/2609.09561 · HTML: https://mlsanity.com/paper/2609.09561/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [PairNorm: Tackling Oversmoothing in GNNs](https://mlsanity.com/paper/1909.12223/) (2019)
- [SpaText: Spatio-Textual Representation for Controllable Image Generation](https://mlsanity.com/paper/2211.14305/) (2022)
- [OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts](https://mlsanity.com/paper/2205.01833/) (2022)
- [Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2405.15234/) (2024)
- [SciRepEval: A Multi-Format Benchmark for Scientific Document Representations](https://mlsanity.com/paper/2211.13308/) (2022)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient](https://mlsanity.com/paper/2405.15304/) (2024)
- [GuardT2I: Defending Text-to-Image Models from Adversarial Prompts](https://mlsanity.com/paper/2403.01446/) (2024)
- [TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering](https://mlsanity.com/paper/1812.09551/) (2018)
- [Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2407.15861/) (2024)
- [HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion](https://mlsanity.com/paper/1910.08194/) (2019)
- [STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths](https://mlsanity.com/paper/2006.10217/) (2020)
- [TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters](https://mlsanity.com/paper/2201.06771/) (2022)
- [SurveyX: Academic Survey Automation via Large Language Models](https://mlsanity.com/paper/2502.14776/) (2025)
- [TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora](https://mlsanity.com/paper/2506.10737/) (2025)
- [TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations](https://mlsanity.com/paper/2202.04887/) (2022)
- [End-to-End Reinforcement Learning for Automatic Taxonomy Induction](https://mlsanity.com/paper/1805.04044/) (2018)
- [Taxonomy Tree Generation from Citation Graph](https://mlsanity.com/paper/2410.03761/) (2024)
- [Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering](https://mlsanity.com/paper/2509.19125/) (2025)
- [Scaling up Dynamic Topic Models](https://mlsanity.com/paper/1602.06049/) (2016)
- [CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs](https://mlsanity.com/paper/2501.15067/) (2025)
- [Rank, Chunk and Expand: Lineage-Oriented Reasoning for Taxonomy Expansion](https://mlsanity.com/paper/2505.13282/) (2025)
- [Self-supervised Topic Taxonomy Discovery in the Box Embedding Space](https://mlsanity.com/paper/2408.15050/) (2024)

## Abstract (arXiv)

Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publication. Existing taxonomy-induction methods are largely leaf-bound and time-agnostic; they tend to force transitional papers into mature leaves and can create topological inversions between ancestors and descendants. We propose EvoTree, a staged framework that decouples conceptual backbone learning from temporal refinement: a graph-aware encoder with distribution-based hierarchical clustering yields a stable taxonomy backbone; temporal fine-tuning then re-attaches marginal papers to internal nodes under monotonic-path constraints; a final LLM pass labels concepts without altering the topology. We release the first annotated benchmark for this task across 11 AI subfields. EvoTree attains the highest NMI and citation-direction accuracy among all baselines and the best concept purity on the annotated benchmark, and is the only method with non-trivial marginal-paper detection on the annotated set.