-
Stanford & UT Austin
- https://jiaxin-pei.github.io/
Stars
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
A PyTorch implementation of "TextFuseNet: Scene Text Detection with Richer Fused Features".
A simple interface to the Project Gutenberg corpus.
A suite of tools for managing crowdsourcing tasks from the inception through to data packaging for research use.
Tools for collecting social media data around focal events
An NLP processing pipeline for characters in fanfiction. Developed by students at Carnegie Mellon University from 2019-2021.
The official repo for SocKET: Social Knowledge Evaluation Tests
Topic Modeling for The New York Times News Dataset
Code for the paper "Modeling Information Change in Science Communication with Semantically Matched Paraphrases" from EMNLP 2022
Official repository for the ICWSM '21 paper "More than meets the tie: Examining the Role of Interpersonal Relationships in Social Networks"
Scaling evaluation of LLM-based opinion summarization in public deliberation.
Official code for the paper: "Multi-User Large Language Model Agents"