TaxoAdapt: Aligning LLM‑Based Multidimensional Taxonomy Construction to Evolving Research Corpora 📚
We introduce TaxoAdapt, a dynamic framework that constructs and adapts multidimensional taxonomies—organized hierarchically across breadth and depth—by iteratively aligning with the evolving content of a target research corpus.
🌱 Dynamic Taxonomy Growth – Instead of static hierarchies, TaxoAdapt incrementally expands its taxonomy structure (both width and depth) in response to the topical distribution of the incoming corpus
papers
📏 Multidimensional Lens – Recognizes that papers contribute along various axes (e.g., methodology, new tasks, evaluation metrics, benchmarks), and models this complexity explicitly
arxiv.org
🤖 LLM‑Guided Classification – Leverages large language models for hierarchical classification, rooted in corpus evidence rather than just pretrained knowledge
📈 Proven Across Time & Domains – Validated on multiple CS conferences’ papers over time, TaxoAdapt yields taxonomies that are 26.5% more granularity‑preserving and 50.4% more coherent compared to strong baselines according to LLM judgments
✨ Efficient & Adaptive – Automatically adapts to new topics and shifts in research trends—cutting down reliance on manual expert curation while keeping structure current and high‑quality
