base on General technology for enabling AI capabilities w/ LLMs and MLLMs <!--# LMOps: Enabling AI w/ LLMs--> # LMOps LMOps is a research initiative on fundamental research and technology for building AI products w/ foundation models, especially on the general technology for enabling AI capabilities w/ LLMs and Generative AI models. - Better Prompts: [Automatic Prompt Optimization](https://arxiv.org/abs/2305.03495), [Promptist](https://arxiv.org/abs/2212.09611), [Extensible prompts](https://arxiv.org/abs/2212.00616), [Universal prompt retrieval](https://arxiv.org/abs/2303.08518), [LLM Retriever](https://arxiv.org/abs/2307.07164), [In-Context Demonstration Selection](https://arxiv.org/abs/2305.14726) - Longer Context: [Structured prompting](https://arxiv.org/abs/2212.06713), [Length-Extrapolatable Transformers](https://arxiv.org/abs/2212.10554) - LLM Alignment: [Alignment via LLM feedback]() - LLM Accelerator (Faster Inference): [Lossless Acceleration of LLMs](https://arxiv.org/abs/2304.04487) - LLM Customization: [Adapt LLM to domains](https://arxiv.org/pdf/2309.09530.pdf) - Fundamentals: [Understanding In-Context Learning](https://arxiv.org/abs/2212.10559) ## Links - [microsoft/unilm](https://github.com/microsoft/unilm): Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities - [microsoft/torchscale](https://github.com/microsoft/torchscale): Transformers at (any) Scale ## News - [Paper Release] Nov, 2023: [In-Context Demonstration Selection with Cross Entropy Difference](https://arxiv.org/abs/2305.14726) (EMNLP 2023) - [Paper Release] Oct, 2023: [Tuna: Instruction Tuning using Feedback from Large Language Models](https://arxiv.org/pdf/2310.13385.pdf) (EMNLP 2023) - [Paper Release] Oct, 2023: [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://arxiv.org/abs/2305.03495) (EMNLP 2023) - [Paper Release] Oct, 2023: [UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation](https://arxiv.org/abs/2303.08518) (EMNLP 2023) - [Paper Release] July, 2023: [Learning to Retrieve In-Context Examples for Large Language Models](https://arxiv.org/abs/2307.07164) - [Paper Release] April, 2023: [Inference with Reference: Lossless Acceleration of Large Language Models](https://arxiv.org/abs/2304.04487) - [Paper Release] Dec, 2022: [Why Can GPT Learn In-Context? Language Models Secretly Perform Finetuning as Meta Optimizers](https://arxiv.org/abs/2212.10559) - [Paper & Model & Demo Release] Dec, 2022: [Optimizing Prompts for Text-to-Image Generation](https://aka.ms/promptist) - [Paper & Code Release] Dec, 2022: [Structured Prompting: Scaling In-Context Learning to 1,000 Examples](https://arxiv.org/abs/2212.06713) - [Paper Release] Nov, 2022: [Extensible Prompts for Language Models](https://arxiv.org/abs/2212.00616) ## Prompt Intelligence Advanced technologies facilitating prompting language models. ### Promptist: reinforcement learning for automatic prompt optimization [Paper] [Optimizing Prompts for Text-to-Image Generation](https://arxiv.org/abs/2212.09611) > - Language models serve as a prompt interface that optimizes user input into model-preferred prompts. > - Learn a language model for automatic prompt optimization via reinforcement learning.  ### Structured Prompting: consume long-sequence prompts in an efficient way [Paper] [Structured Prompting: Scaling In-Context Learning to 1,000 Examples](https://arxiv.org/abs/2212.06713) - Example use cases: > 1) Prepend (many) retrieved (long) documents as context in GPT. > 2) Scale in-context learning to many demonstration examples.  ### X-Prompt: extensible prompts beyond NL for descriptive instructions [Paper] [Extensible Prompts for Language Models](https://arxiv.org/abs/2212.00616) > - Extensible interface allowing prompting LLMs beyond natural language for fine-grain specifications > - Context-guided imaginary word learning for general usability  ## LLMA: LLM Accelerators ### Accelerate LLM Inference with References [Paper] [Inference with Reference: Lossless Acceleration of Large Language Models](https://arxiv.org/abs/2304.04487) > - Outputs of LLMs often have significant overlaps with some references (e.g., retrieved documents). > - LLMA losslessly accelerate the inference of LLMs by copying and verifying text spans from references into the LLM inputs. > - Applicable to important LLM scenarios such as retrieval-augmented generation and multi-turn conversations. > - Achieves 2~3 times speed-up without additional models.  ## Fundamental Understanding of LLMs ### Understanding In-Context Learning [Paper] [Why Can GPT Learn In-Context? Language Models Secretly Perform Finetuning as Meta Optimizers](https://arxiv.org/abs/2212.10559) > - According to the demonstration examples, GPT produces meta gradients for In-Context Learning (ICL) through forward computation. ICL works by applying these meta gradients to the model through attention. > - The meta optimization process of ICL shares a dual view with finetuning that explicitly updates the model parameters with back-propagated gradients. > - We can translate optimization algorithms (such as SGD with Momentum) to their corresponding Transformer architectures.  ## Hiring: [aka.ms/GeneralAI](https://aka.ms/GeneralAI) We are hiring at all levels (including FTE researchers and interns)! If you are interested in working with us on Foundation Models (aka large-scale pre-trained models) and AGI, NLP, MT, Speech, Document AI and Multimodal AI, please send your resume to <a href="mailto:[email protected]" class="x-hidden-focus">[email protected]</a>. ## License This project is licensed under the license found in the LICENSE file in the root directory of this source tree. [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct) ### Contact Information For help or issues using the pre-trained models, please submit a GitHub issue. For other communications, please contact [Furu Wei](http://gitnlp.org/) (`[email protected]`). ", Assign "at most 3 tags" to the expected json: {"id":"3201","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"