Paper List

NLP & LLM & RAG & GenAI & Agent 에 대한 최신 논문 동향을 파악하고 리스트를 정리해보자!

Paper Review

• Attention is all you need

• CoVe : Chain of Verifiction Reduces Hallucination in Large Language Models

• RAG Survey : A Survey on Retrieval-Augmented Text Generation for Large Language Models

• Interleaving Retrieval with Chain-of-Thought for Knowledge-Intensive Multi-Step Questions

• Taka a Step Back : Evoking Reasoning via Abstraction in Large Language Models

Paper List

• EEVE : Efficient and Effective Vocabulary Expansion Towards Mulitilingual Large Language Models

  • https://arxiv.org/pdf/2402.14714.pdf

• Will GPT-4 Run Doom?

  • https://arxiv.org/pdf/2403.05468.pdf

• PiSSA : Principal Singular Values and Singular Vectors Adaptation of Large Language Models

  • https://arxiv.org/pdf/2404.02948.pdf

• RAFT : Adapting Language Model to Domain Specific RAG

  • https://arxiv.org/pdf/2403.10131.pdf

• ReALM : Reference Resolution As Language Modeling

  • https://arxiv.org/pdf/2403.20329.pdf

• WavLLM : Towards Robust and Adaptive Speech Large Language Model

  • https://arxiv.org/pdf/2404.00656.pdf

• Batch Calibration : Rethinking Calibration for In-Context Learning and Prompt Engineering

  • https://arxiv.org/pdf/2309.17249.pdf?fbclid=IwAR1CxzuKE5BqpKBZk61xlUX3qJNKZ6rI9Z0gGlHSRhsyrvpQ44Ga0wraCu4_aem_ATjGyhm21zmG3fZ5OZZMhj9yCR4tqUDuCHcl9hGTxBGx_yZzV5BjOj92NFnrWpYqT8YmO9PvqfI1DyQZcujKnDI1

• Tokenizer Choice For LLM Training: Negligible or Crucial?

  • https://arxiv.org/pdf/2310.08754.pdf?fbclid=IwAR1uR9YayRIg7CqTzPnGCc8ikdVCBaSdrnaM-u5exJb2WJiZcn1v9Pzd6z4_aem_AYr3BSBDwa0oghSm7lM3-ub30Dq3LnEOg8b97C3o6yoKYbF3lwRNa-wEsACUdUCRolj_zZ025P9dpuqv_dGZMcWk

• AIOS : LLM Agent Operating System

  • Link : https://arxiv.org/pdf/2403.16971.pdf

• Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge

  • Link : https://arxiv.org/pdf/2403.01432.pdf

• FollowIR : Evaluating and Teaching Information Retrieval Models to Follow Instructions

  • Link : https://arxiv.org/abs/2403.15246

• Stealing Part of a Production Language Model

  • Link : https://arxiv.org/pdf/2403.06634.pdf

• The Claude 3 Model Family: Opus, Sonnet, Haiku

  • Link : https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf?utm_source=pytorchkr

• Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap

  • Link : https://arxiv.org/pdf/2402.19450.pdf

• GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

  • Link : https://arxiv.org/pdf/2403.03507.pdf

• Can Large Language Models Reason and Plan?

  • Link : https://arxiv.org/pdf/2403.04121.pdf

• ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks

  • https://arxiv.org/pdf/2303.15056.pdf

• Retrieval-Augmented Generation for AI-Generated Content: A Survey

  • Link : https://arxiv.org/pdf/2402.19473v1.pdf

• KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents

  • Link : https://arxiv.org/pdf/2403.03101.pdf

• Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

  • Link : https://arxiv.org/pdf/2402.17177v2.pdf

• SaulLM-7B: A pioneering Large Language Model for Law

  • Link : https://arxiv.org/pdf/2403.03883.pdf

• Design2Code: How Far Are We From Automating Front-End Engineering?

  • Link : https://arxiv.org/pdf/2403.03163.pdf

• TripoSR: Fast 3D Object Reconstruction from a Single Image

  • Link : https://arxiv.org/pdf/2403.02151v1.pdf

• MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training

  • Link : https://arxiv.org/pdf/2311.17049.pdf

• MoE : Towards Understanding Mixture of Experts in Deep Learning

  • Link : https://arxiv.org/pdf/2208.02813.pdf

• SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures

  • Link : https://arxiv.org/pdf/2402.03620.pdf

• CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models

  • Link : https://arxiv.org/pdf/2212.07769.pdf