details of the close kind

Important Papers on LLMs and GPTs

Large language models, or LLMs, have varying levels of training and parameters. LLMs contain hundreds of millions or billions of documents and words that have been said over time. Few new business and social ideas are ever discovered. For decades, the words to describe any task have been uttered and captured. Mature LLMs (none exist in 2023) will provide trusted information. Encyclopedia Britannica was a trusted source in the 1960s and 1970s. A number of competing encyclopedias were sold, as a number of key LLMs will emerge.

It’s kind of like the discussions on oversize rings in an engine or memory speed in a computer. Ford vs Chevy. Bank of America vs Chase. The difference was rarely seen in a meaningful way.

These are titles and links to seminal papers on underlying AI research.

ResearchLLaMA: Open and Efficient Foundation Language Models
ResearchSemantic reconstruction of continuous language from non-invasive brain recordings
ResearchIs Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
ResearchUnlimiformer: Long-Range Transformers with Unlimited Length Input
ResearchDistill or Annotate? Cost-Efficient Fine-Tuning of Compact Models
ResearchLanguage Models: GPT and GPT-2
ResearchTransformer Puzzles
ResearchLlamaIndex 0.6.0: A New Query Interface Over your Data
ResearchThe Ultimate Battle of Language Models: Lit-LLaMA vs GPT3.5 vs Bloom vs …
ResearchHarnessing LLMs
ResearchHow to train your own Large Language Models
ResearchScaling Forward Gradient With Local Losses
ResearchIntroducing Lamini, the LLM Engine for Rapidly Customizing Models
ResearchCategorification of Group Equivariant Neural Networks
ResearchHarnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond
ResearchThe Practical Guides for Large Language Models
ResearchIntroduction to LangChain: A Framework for LLM Powered Applications
ResearchMulti-Party Chat: Conversational Agents in Group Settings with Humans and Models
ResearchA large-scale comparison of human-written versus ChatGPT-generated essays
ResearchEvaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery
ResearchA Cookbook of Self-Supervised Learning
ResearchNeMo Guardrails
ResearchAudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
ResearchState Spaces Aren’t Enough: Machine Translation Needs Attention
ResearchAnswering Questions by Meta-Reasoning over Multiple Chains of Thought
ResearchGetting Started with LangChain: A Beginner’s Guide to Building LLM-Powered Applications
ResearchGenerative AI at Work
ResearchLLM+P: Empowering Large Language Models with Optimal Planning Proficiency
ResearchLanguage Modeling using LMUs: 10x Better Data Efficiency or Improved Scaling Compared to Transformers
ResearchImproving Document Retrieval with Contextual Compression
ResearchThe Embedding Archives: Millions of Wikipedia Article Embeddings in Many Languages
ResearchHugging Face Hub
ResearchEffective Instruction Tuning
ResearchReinforcement Learning with Human Feedback (RLHF)
ResearchLanguage Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes
ResearchTransformer Math 101
ResearchOpen-source research on large language models (LLMs)
ResearchA visual guide to transformers
ResearchEnhancing Vision-language Understanding with Advanced Large Language Models
ResearchTransformer: Attention Is All You Need
ResearchLLMs on personal devices
ResearchLLM Source Context Evaluation
ResearchGenerative Agents: Interactive Simulacra of Human Behavior
ResearchShall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
ResearchAuto-evaluate LLM Q+A chains
ResearchUnderstanding Diffusion Models: A Unified Perspective
ResearchBuilding LLM applications for production
ResearchBoosted Prompt Ensembles for Large Language Models
ResearchTeaching Large Language Models to Self-Debug
ResearchThe Power of Scale for Parameter-Efficient Prompt Tuning
ResearchMultimodal Procedural Planning via Dual Text-Image Prompting
ResearchAre Emergent Abilities of Large Language Models a Mirage?