NLP/논문이해 (65) 썸네일형 리스트형 [논문이해] GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher 논문명: GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher 논문링크: https://arxiv.org/abs/2308.06463 GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher Safety lies at the core of the development of Large Language Models (LLMs). There is ample work on aligning LLMs with human ethics and preferences, including data filtering in pretraining, supervised fine-tuning, reinforce.. [논문이해] Dataset Distillation with Attention Labels for Fine-tuning BERT 논문명: Dataset Distillation with Attention Labels for Fine-tuning BERT 논문링크: https://aclanthology.org/2023.acl-short.12/ Dataset Distillation with Attention Labels for Fine-tuning BERT Aru Maekawa, Naoki Kobayashi, Kotaro Funakoshi, Manabu Okumura. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2023. aclanthology.org 아이디어만 정리합니다 Da.. [논문이해] Query2doc: Query Expansion with Large Language Models 논문명: Query2doc: Query Expansion with Large Language Models 논문링크: https://arxiv.org/abs/2303.07678 Query2doc: Query Expansion with Large Language Models This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems. The proposed method first generates pseudo-documents by few-shot prompting large language models (LLM.. [논문이해] Block-Skim: Efficient Question Answering for Transformer 논문명: Block-Skim: Efficient Question Answering for Transformer 논문링크: https://arxiv.org/abs/2112.08560 Block-Skim: Efficient Question Answering for Transformer Transformer models have achieved promising results on natural language processing (NLP) tasks including extractive question answering (QA). Common Transformer encoders used in NLP tasks process the hidden states of all input tokens in the c.. [논문이해] What learning algorithm is in-context learning? Investigations with linear models 논문명: What learning algorithm is in-context learning? Investigations with linear models 논문링크: https://arxiv.org/abs/2211.15661 What learning algorithm is in-context learning? Investigations with linear models Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples $(x, f(x))$ prese.. [논문이해] Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers 논문명: Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers 논문링크: https://arxiv.org/abs/2212.10559 Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers Large pretrained language models have shown surprising in-context learning (ICL) ability. With a few demonstration input-label pairs, they can predict t.. [논문이해] Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations 논문명: Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations 논문링크: https://arxiv.org/abs/2205.12685 Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations Despite recent explosion of interests in in-context learning, the underlying mechanism and the precise impact of the quality of demonstrations remain elusive. Intuitively, ground-truth labels should have as.. [논문이해] Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations 논문명:Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations 논문링크: https://arxiv.org/abs/2212.09865 Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations Although large language models can be prompted for both zero- and few-shot learning, performance drops significantly when no demonstrations are available. In this paper, we introduce Z-ICL, a new zero-shot method that closes th.. 이전 1 ··· 3 4 5 6 7 8 9 다음
