Magis-Bench is a new benchmark of 74 magistrate-level legal writing tasks from Brazilian exams where the strongest LLMs reach only 6.97/10, showing judicial reasoning remains difficult for current models.
Reproducing nevir: Negation in neural information retrieval
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 4roles
dataset 1polarities
use dataset 1representative citing papers
TikTok formally complies with DSA rules against profiling minors but delivers 5-8 times stronger interest-based targeting through undisclosed influencer and promotional content.
A two-stage adapter method aligns query and document embedding spaces to improve dense retrieval for complex queries using lightweight encoders and few labels.
Passages made from high-convergence sentences improve LLM performance on inferential questions compared to cosine similarity selection.
citing papers explorer
-
Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks
Magis-Bench is a new benchmark of 74 magistrate-level legal writing tasks from Brazilian exams where the strongest LLMs reach only 6.97/10, showing judicial reasoning remains difficult for current models.
-
The DSA's Blind Spot: Algorithmic Audit of Advertising and Minor Profiling on TikTok
TikTok formally complies with DSA rules against profiling minors but delivers 5-8 times stronger interest-based targeting through undisclosed influencer and promotional content.
-
Align then Train: Efficient Retrieval Adapter Learning
A two-stage adapter method aligns query and document embedding spaces to improve dense retrieval for complex queries using lightweight encoders and few labels.
-
Context Convergence Improves Answering Inferential Questions
Passages made from high-convergence sentences improve LLM performance on inferential questions compared to cosine similarity selection.