Pinned Repositories
BamTwoogle
The BamTwoogle dataset accompanies "ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent" paper (https://arxiv.org/abs/2312.10003). It was written to be a complementary, slightly more challenging sequel to Bamboogle dataset. It addresses some of the shortcomings of Bamboogle we discovered while performing human evals for the paper.
cf_triviaqa
The CF-TriviaQA dataset accompanies "Hallucination Augmented Recitations for Language Models" paper (https://arxiv.org/abs/2311.07424). It is a counterfactual open book QA dataset generated from the TriviaQA dataset using Hallucination Augmented Recitations (HAR) approach, with the purpose of improving attribution in LLMs.
RLinOpenaiGym
The code for Stanford's AA228/CS238 final project
SQuAD
The code for Stanford's CS224n final project
TextWorld
The code for Stanford's CS230 final project
raksitov's Repositories
raksitov/RLinOpenaiGym
The code for Stanford's AA228/CS238 final project
raksitov/SQuAD
The code for Stanford's CS224n final project
raksitov/TextWorld
The code for Stanford's CS230 final project