Cost-of-Pass: An Economic Framework for Evaluating Language Models

Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory

A pipeline for finding racially restrictive covenants in collections of property deeds

Code repository for "Statistical Uncertainty in Word Embeddings: GloVe-V"

Belief in the Machine: Investigating Epistemological Blind Spots of Language Models

Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding

ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.

Useful functions for working with small molecules

Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI

A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021 (Bianchi et al.).

String-to-String Algorithms for Natural Language Processing

This repository contains the code for CHEEREIO, which supports data assimilation and emissions inversions for arbitrary runs of the GEOS-Chem chemical transport model via an ensemble approach (i.e.…

DIBS is an implementation of a basic controlled digital lending (CDL) system using IIIF to make scanned books available for time-limited viewing.

Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding

Python client for Moss: A System for Detecting Software Similarity

Code for our EMNLP '22 paper "Fixing Model Bugs with Natural Language Patches"

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

Neural Networks and the Chomsky Hierarchy

The Harvard USPTO Patent Dataset

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

Monte Carlo Tree Search for Interpreting Stress Conditions in Natural Language

MARNNs Can Learn Generalized Dyck Languages

Typed argument parser for Python

Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

Pip-installable differentiable stacks in PyTorch!

On Evaluating the Generalization of LSTMs in Formal Languages

Neural variational inference and learning in undirected graphical models http://www.stanford.edu/~kuleshov/papers/nips2017.pdf