yakazimir

awesome-deliberative-prompting

Awesome deliberative prompting: How to ask LLMs to produce reliable reasoning and make reason-responsive decisions.

language_fragments

cot-eval

A framework for evaluating the effectiveness of chain-of-thought reasoning in language models.

logikon

Analyzing and scoring reasoning traces of LLMs

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

outlines

Structured Text Generation

spaCy

💫 Industrial-strength Natural Language Processing (NLP) in Python

Code-Datasets

Original data for the text to code experiments of Richardson and Kuhn

auction-arena

Source code for our paper: "Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena"

OLMo-Eval

Evaluation suite for LLMs

lmql

A language for constraint-guided and efficient LLM programming.

esslli_neural_symbolic

Course resources and notes for the ESSLLI 2023 course on neural symbolic methods.

recoma

Reasoning by Communicating with Agents

situation_modeling

Code for situation modeling, EMNLP 2022

semantic-loss-pytorch

PyPSDD porting to Python 3 + PyTorch equivalent tree construction.

ChatGPT-vs.-BERT

🎁[ChatGPT4NLU] A Comparative Study on ChatGPT and Fine-tuned BERT

paraphrase-nli

disco

Generating diverse counterfactual data for Natural Language Understanding tasks using Large Language Models (LLMs). The generator supports GPT-3, ChatGPT, and GPT-4.

catwalk

This project studies the performance and robustness of language models and task-adaptation methods.

curriculum-ling

Curriculum is a new format of NLI benchmark for evaluation of broad-coverage linguistic phenomena. This linguistic-phenomena-driven benchmark can serve as an effective tool for diagnosing model behavior and verifying model learning quality.

pylon

NeSyEntropy

problog

ProbLog is a Probabilistic Logic Programming Language for logic programs with probabilities.

CommaQA

Code and Dataset for Learning to Solve Complex Tasks by Talking to Agents

beaker-gantry

Gantry streamlines running Python experiments in Beaker by managing containers and boilerplate for you

deepa2

Resources for creating, importing and using DeepA2 Argument Analysis Framework datasets

spacy-clausie

Implementation of the ClausIE information extraction system for python+spacy

PySDD

Python package for Sentential Decision Diagrams (SDD)

epikat

Epistemic Reasoning in KAT

correlating-neural-and-symbolic-representations-of-language

Code for the paper https://arxiv.org/abs/1905.06401