Inspect: A framework for large language model evaluations

Up-to-date version of labs for ISLP

모두의 한국어 텍스트 분석 with 파이썬

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

ethicalVsUnethicalQuestionsKor로 데이터 증강 필요

Topic-Aware Convolutional Neural Networks for Extreme Summarization

This tool helps automatic generation of grammatically valid synthetic Code-mixed data by utilizing linguistic theories such as Equivalence Constant Theory and Matrix Language Theory.

ChatGPT의 RLHF를 학습을 위한 3가지 step별 한국어 데이터셋

Korean Commonsense Knowledge Graph