Researchers have introduced LegalPincite, a new dataset designed to improve legal information retrieval by providing paragraph-level citation annotations. This dataset, derived from Court of Justice of the European Union judgments, addresses limitations in existing legal IR datasets by removing query text data leakage and including all paragraphs, not just those that are cited. LegalPincite supports the development and evaluation of retrieval methods at multiple granularities, including case-to-case, paragraph-to-case, and paragraph-to-paragraph retrieval. AI
IMPACT This dataset could advance the development of more accurate legal AI systems by enabling better training and evaluation of paragraph-level citation retrieval.
RANK_REASON The cluster describes a new dataset for legal information retrieval, presented in an academic paper.
Read on Hugging Face Daily Papers →
- alphaXiv
- CatalyzeX
- Connected Papers
- CORE Recommender
- Court of Justice of the European Union
- DagsHub
- Gotit.pub
- Hugging Face
- Influence Flower
- information retrieval
- LegalPincite
- Litmaps
- ScienceCast
- scite Smart Citations
- Theresia Veronika Rampisela
- EUR-Lex
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
