Mirac Suzgun

BIG-Bench-Hard. Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

meta-prompting. Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding

dynamic-cheatsheet. Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory

hupd. The Harvard USPTO Patent Dataset

prompt-and-rerank. Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Textual Style Transfer

belief-in-the-machine. Belief in the Machine: Investigating Epistemological Blind Spots of Language Models

crowd-sampling. Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding

marnns. MARNNs Can Learn Generalized Dyck Languages

lstm-eval. On Evaluating the Generalization of LSTMs in Formal Languages

ai-as-news-intermediaries. Jupyter Notebook

TankTouble.2.01. Java Project