Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Awesome papers on Language-Model-as-a-Service (LMaaS)
| Date | Stars |
|---|---|
| 2026-07-31 | 545 |
| 2026-08-03 | 545 |
| 2026-08-06 | 545 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Language Model as a Service (LMaaS)   This is a curated list of "Language-Model-as-a-Service (LMaaS)" papers, which is mainly maintained by [Tianxiang Sun](https://txsun1997.github.io/). We strongly encourage the NLP researchers who are interested in this topic to make pull request to add or update the papers (See [Contributing](#contributing)). Watch this repository for the latest updates! ## Updates - 2022/7/7: Write a [blog](https://zhuanlan.zhihu.com/p/538857729) (in Chinese) - 2022/7/4: Create this paper list ## Contents - [Introduction](#introduction) - [Scope](#scope) - [Advantages](#advantages) - [Keywords](#keywords) - [Papers](#papers) - [Text Prompt](#text-prompt) - [In-Context Learning](#in-context-learning) - [Black-Box Optimization](#black-box-optimization) - [Feature-based Learning](#feature-based-learning) - [Data Generation](#data-generation) - [Contributing](#contributing) ## Introduction Due to commercial reasons and expensive tuning cost, pre-trained large language models (LLMs) such as GPT-3 are usually released as a service instead of open sourcing model weights. We call this scenario "**Language-Model-as-a-Service (LMaaS)**" (the term is originally used in [our ICML'2022 paper](https://arxiv.org/abs/2201.03514)). In such a scenario, users can access the powerful LLMs through their inference APIs. The service of LLMs has powered many use cases (See [GPT-3 Demo](https://gpt3demo.com/)). In contrast to fine-tuning, LMaaS allows a single general purpose LLM to serve many difference tasks and therefore is highly deployment-efficient. Nevertheless, how to adapt LLMs to target tasks without access to their parameters and gradients is a challenge. To make LLMs benefit a wider audience, we collect papers that fit into this scenario to facilitate future research.  ### Scope Which papers fit into the scenario of LMaaS? We mainly consider papers that adapt LLMs to downstream tasks without accessing the model parameters and the gradients. Though fine-tuned LLMs can also be services after deployment, they are limited to solve a single task for limited audience. In our scope, we prefer serving general purpose models for a variety of users. In existing literature, there are several lines of research that fit into LMaaS: - **Text prompt**. By manually or automatically designing task-specific text prompts, users can solve the target task of interest by conditioning frozen LLMs. - **In-context learning**. Users can provide a few examples in the input at inference time to help LLMs to rapidly adapt to the target task. - **Black-box optimization**. By tuning a small portion of parameters (e.g., continuous prompt) with only the access of the LLM's output probability via black-box optimization, users can solve target tasks with a small training set. - **Feature-based learning**. LLMs can serve as a feature extractor, on which users can build some learnable task-specific modules to perform classification or generation. - **Data Generation**. Generative LLMs can be used to generate a dataset of labeled text pairs from scratch, which is then used to locally train a much smaller model. The boundary between *text prompt* and *in-context learning* is a bit blurred. In this repo, the *text prompt* category contains papers that do not use labeled samples, while the *in-context learning* category is comprised of papers that include labeled samples in the prompts. **Note:** A related (and partially overlapped) topic is *prompt-based learning*, which aims to solve downstream tasks using general purpose LLMs by converting input and output with some template and verbalizer, respectively. However, most works in prompt-based learning require the access to model parameters and gradients, and therefore do
Excerpt of 36,244 characters
Read on GitHub
Tianxiang Sun · @analemmaai · China
66
5
2
Tianbao Xie · The University of Hong Kong · Hong Kong
2
Zhengfu He@SII · Shanghai Innovation Institute
1
1
xyliu · Fudan University · China
1
1
Fábio Perez · Brazil
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4aeaad66e0bcab33, topic:nlp, topic:natural-language-processing