If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs
Paper
•
2412.04144
•
Published
•
4
CLINT
AI & ML interests
None defined yet.
Recent Activity
View all activity
clintuning's activity
tomsherborne
authored
a
paper
about 1 month ago
akariasai
authored
a
paper
about 2 months ago
akariasai
authored
a
paper
3 months ago
hilagonen
authored
7
papers
5 months ago
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
Paper
•
2004.07667
•
Published
Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark
Paper
•
2311.09122
•
Published
•
7
Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models
Paper
•
2401.10440
•
Published
MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling
Paper
•
2403.10691
•
Published
XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models
Paper
•
2301.10472
•
Published
MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization
Paper
•
2407.08818
•
Published
Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models
Paper
•
2408.06518
•
Published
akariasai
authored
a
paper
6 months ago
tomsherborne
authored
a
paper
6 months ago
tomsherborne
authored
2
papers
9 months ago
machelreid
authored
a
paper
10 months ago
machelreid
authored
a
paper
11 months ago
akariasai
authored
4
papers
11 months ago
Fine-grained Hallucination Detection and Editing for Language Models
Paper
•
2401.06855
•
Published
•
4
When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
Paper
•
2212.10511
•
Published
•
1
Task-aware Retrieval with Instructions
Paper
•
2211.09260
•
Published
XOR QA: Cross-lingual Open-Retrieval Question Answering
Paper
•
2010.11856
•
Published