Below are some of my key research contributions:
LLM applications for insurance document automation using parameter-efficient fine-tuning and analysis of calibration …...
Ablation study of neural network components for forecasting, finding gating and attention improve RNNs while recurrence …...
Enhanced TABME benchmark for page stream segmentation, creating TABME++, showing fine-tuned decoder-based LLMs …...
Analytical model of Word2Vec and GloVe statistics. First analytical solution to Word2Vec's softmax skip-gram with bias …...
Investigation into EigenNoise, a data-free initialization scheme for word vectors that approaches pre-trained model …...
Investigation into whether universal adversarial triggers can control both topic and stance of GPT-2's generated text …...
NewsTweet dataset and pipeline for studying embedded tweets in online news. Analysis shows 13% of stories contain …...
Investigation into follower dynamics on high-profile Twitter accounts, documenting sub-second spikes, saw-tooth …...
Explores a data-driven approach to construct a WordNet-like semantic network using the entirety of the noisy, …...