Paper Reviews
1.[논문리뷰] Solving Quantitative Reasoning Problems with Language Models : Minerva
다양한 자연어 task에서 성공을 거둔 거대 언어 모델.하지만 양적 추론(quantitative reasoning)이 필요한 task에서 고전하였다. ex) 수학, 과학, 공학 문제들…💡 Quantitative Reasoning 여러 방면에서 모델의 능력을 시험할
2.[논문리뷰] Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
We explore how generating a chain of thought—a series of intermediate reasoningsteps—significantly improves the ability of large language models to pe
3.[논문리뷰] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent
4.[논문리뷰] Learning to summarize from human feedback
As language models become more powerful, training and evaluation are increasinglybottlenecked by the data and metrics used for a particular task. For
5.[논문리뷰] Attention is all you need
The dominant sequence transduction models are based on complex recurrent orconvolutional neural networks that include an encoder and a decoder. The be
6.[논문리뷰] Improving Language Understanding by Generative Pre-Training
Natural language understanding comprises a wide range of diverse tasks suchas textual entailment, question answering, semantic similarity assessment,
7.[논문리뷰] An Improved Baseline for Sentence-level Relation Extraction
Sentence-level relation extraction (RE) aims at identifying the relationship between two entities in a sentence. Many efforts have been devoted to thi
8.[논문 리뷰] Language Models are Unsupervised Multitask Learners
거대 생성모델의 시초가 되는 GPT의 변천 과정을 살펴보기 위해 선택했다.언어 모델이 다운스트림 태스크에서 zero-shot setting 만으로 다양한 분야에서 좋은 성능을 보일 수 있음을 증명하였다.지금까지의 연구는 단일 과제에 특화된 단일 모델을 개발하는데 치중되