Two new research papers introduce frameworks for enhancing scientific taxonomies using Large Language Models (LLMs) and embeddings. The first, ReLTEx, focuses on reliable LLM-based taxonomy expansion by combining LLM generation with structure-aware validation to reduce hallucinations and improve consistency. The second, SCALE, extends the OpenAlex taxonomy by creating a new layer of scientific Concepts using embeddings and LLMs to organize semantically related terms into coherent units, enabling finer-grained scholarly classification and analysis. AI
IMPACT These frameworks could enable more detailed and accurate classification of scientific literature, improving research monitoring and knowledge organization.
RANK_REASON Two academic papers published on arXiv introducing novel frameworks for taxonomy expansion using LLMs and embeddings.
- arXiv
- embeddings
- Hugging Face
- LLMs
- OpenAlex
- SCALE
- alphaXiv
- arXivLabs
- CatalyzeX Code Finder for Papers
- Connected Papers
- CORE Recommender
- DagsHub
- Gotit.pub
- Large Language Models
- Litmaps
- ReLTEx
- ScienceCast
- scite Smart Citations
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
