NLP/논문이해 (65) 썸네일형 리스트형 [논문이해] DPO 손실함수는 어떻게 탄생했는가 이 글을 이해하려면, RLHF에 대한 이해가 필요하니 아래 블로그부터 읽으면 좋다. https://heygeronimo.tistory.com/122 [논문이해] training language models to follow instructions with human feedback논문을 이해하고 싶다면 아래 글을 읽으세요. 너무 잘 써서 이것보다 더 잘 쓸 자신이 없어요. https://taeyuplab.tistory.com/10 [논문 리뷰] InstructGPT: Training language models to follow instructions with human feedbackheygeronimo.tistory.com 이 글의 관심사는 오로지 수학적인 유도 과정이다. 나처럼 인공지능을 머신러닝이.. [논문이해] training language models to follow instructions with human feedback 논문을 이해하고 싶다면 아래 글을 읽으세요. 너무 잘 써서 이것보다 더 잘 쓸 자신이 없어요. https://taeyuplab.tistory.com/10 [논문 리뷰] InstructGPT: Training language models to follow instructions with human feedback이 글에서는 InstructGPT를 제안한 논문인 Training language models to follow instructions with human feedback에 대해 살펴볼 것이다. 본 논문은 GPT-1, GPT-2, GPT-3 논문을 발표한 OpenAI로부터 2022년 NeurIPS에 발표되었다.taeyuplab.tistory.com 근데 논문만 읽고서는 이해가 잘 안되기도 합니다. .. [논문이해] INFO-RAG: Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation 논문명: Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation(INFO-RAG 라고 부르네요) 논문링크: https://arxiv.org/abs/2402.18150 Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented GenerationRetrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating additional information from retriev.. [논문이해] RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training 논문명: RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training논문 링크: https://paperswithcode.com/paper/ra-clip-retrieval-augmented-contrastive Papers with Code - RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-TrainingNo code available yet.paperswithcode.com 핵심만 정리합니다문제점CLIP은 대성공한 방법론인데, 데이터를 많이 필요로 하고 모든 데이터를 파라미터로 기억하기엔 방대함online retrieval 을 통해서 지식을 보강하면 되는 방법론 'RA-CLIP'을.. [논문이해] RETRIEVAL-ENHANCED CONTRASTIVE VISION-TEXT MODELS 논문명: RETRIEVAL-ENHANCED CONTRASTIVE VISION-TEXT MODELS논문 링크: https://arxiv.org/abs/2306.07196 Retrieval-Enhanced Contrastive Vision-Text ModelsContrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from the pre-trainin.. [논문이해] Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned 논문명: Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned논문 링크: https://arxiv.org/abs/1905.09418 Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be PrunedMulti-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate t.. [논문이해] DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models 논문명: DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models논문 링크: https://arxiv.org/abs/2309.03883 DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language ModelsDespite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i.e., generating content that deviates from facts seen during pretraining. We propose a simple.. [논문이해] Contrastive Decoding: Open-ended Text Generation as Optimization 논문명: Contrastive Decoding: Open-ended Text Generation as Optimization논문 링크: https://arxiv.org/abs/2210.15097 Contrastive Decoding: Open-ended Text Generation as OptimizationGiven a language model (LM), maximum probability is a poor decoding objective for open-ended generation, because it produces short and repetitive text. On the other hand, sampling can often produce incoherent text that drifts.. 이전 1 2 3 4 ··· 9 다음 목록 더보기
