ELREA (2024): Expert ensembles framework using gradient-based clustering to improve LLM performance across diverse tasks
G&O (2024): Methods for fine-tuning and using LLMs to extract structured information from unstructured documents
ProgGen (2024): Using LLMs to generate pseudo datasets for supervising smaller task-specific models like BERT
Minesweeper (2023): Investigating whether LLM reasoning abilities are intrinsic or mimicry of training data patterns
CHMM (2021), Sparse CHMM (2022), Wrench (2021), Ren et al. (2020): Series of works on weakly-supervised named entity recognition and text classification
TrENC (2023): Transformer-based DOM node classifiers for HTML information extraction
MUBen (2024): Benchmarking uncertainty quantification methods for molecular property prediction
GuiG (2020): Syntax-guided paraphrase generation using constituency parsing tags to enhance text diversity and quality
Li et al. (2020), Xia et al. (2021): Research on radar SCG signal processing and understanding during master's studies