Taxon uses a mixture-of-experts architecture and LLM-derived semantic verification to achieve state-of-the-art performance on hierarchical tax code prediction and has been deployed in production at Alibaba.
TnT-LLM: Text mining at scale with large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SC-Taxo adds bidirectional heading generation and peer semantic dependency modeling to LLMs to produce taxonomies with improved hierarchy alignment and heading quality on scientific literature benchmarks.
citing papers explorer
-
Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance
Taxon uses a mixture-of-experts architecture and LLM-derived semantic verification to achieve state-of-the-art performance on hierarchical tax code prediction and has been deployed in production at Alibaba.
-
SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models
SC-Taxo adds bidirectional heading generation and peer semantic dependency modeling to LLMs to produce taxonomies with improved hierarchy alignment and heading quality on scientific literature benchmarks.