Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval
Paper
•
2505.16967
•
Published
•
16
Shvets
ashvets
·
AI & ML interests
None yet
Recent Activity
upvoted
an
article
17 days ago
CircleGuardBench: New Standard for Evaluating AI Moderation Models
liked
a Space
about 2 months ago
AmenRa/guardbench-leaderboard
Organizations
ashvets's activity
upvoted
a
paper
1 day ago
upvoted
an
article
17 days ago
Article
CircleGuardBench: New Standard for Evaluating AI Moderation Models
By
and 7 others
•
•
52
liked
a
Space
about 2 months ago