Retrieval Augmented Generation Compositionality
Paper • 2610.29722 • Published • 35
AI & ML interests
Pretraining data constrained and cognitively relevant baby LLMs
Recent Activity
View all activity
Papers
BabyLM Turns 4: Call for Papers for the 2026 BabyLM Workshop
BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data
borgr
authored 4
papers 7 days ago
robinhad
authored 2
papers about 2 months ago
borgr
authored 14
papers 3 months ago
LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content
Paper • 2410.10783 • Published • 26
Unforgettable Generalization in Language Models
Paper • 2409.02228 • Published
Learning to combine Grammatical Error Corrections
Paper • 1906.03897 • Published
Cluster & Tune: Boost Cold Start Performance in Text Classification
Paper • 2203.10581 • Published
The Language of Legal and Illegal Activity on the Darknet
Paper • 1905.05543 • Published
Classifying Syntactic Errors in Learner Language
Paper • 2010.11032 • Published
Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours
Paper • 2208.01483 • Published
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
Paper • 2602.16763 • Published
Automatically Extracting Challenge Sets for Non local Phenomena in Neural Machine Translation
Paper • 1909.06814 • Published
Label-Efficient Model Selection for Text Generation
Paper • 2402.07891 • Published
Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs
Paper • 2408.10646 • Published
Mediators in Determining what Processing BERT Performs First
Paper • 2104.06400 • Published
Lossless and Near-Lossless Compression for Foundation Models
Paper • 2404.15198 • Published
The Mighty ToRR: A Benchmark for Table Reasoning and Robustness
Paper • 2502.19412 • Published