# RUCAIBox/LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

Repository: https://github.com/RUCAIBox/LLMSurvey
Canonical: https://ross.abutalabs.com/products/llmsurvey
Homepage: https://arxiv.org/abs/2303.18223
Language: Python
License Family: other
Topics: chain-of-thought, chatgpt, in-context-learning, instruction-tuning, large-language-models, llm, llms, natural-language-processing, pre-trained-language-models, pre-training, rlhf
Last push: 2025-03-11T09:51:42+00:00

## Health v2 (maintenance only)
Score: 35/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 10, release rhythm 35, longevity 90
- inputs: {"age_days": 1268, "days_push": 540, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12206, forks 931 (observed 2026-08-28T04:10:52.035146+00:00)

## What it is
The official repository accompanying the survey paper 'A Survey of Large Language Models', collecting papers and resources on LLMs including pre-training, instruction tuning, RLHF, and chain-of-thought reasoning. It also offers a Chinese introductory book and is regularly updated with new content such as long CoT reasoning.

## Use cases
- learn about large language models from scratch
- find a survey of LLM pre-training and alignment techniques
- understand RLHF and instruction tuning
- get an overview of chain-of-thought and long CoT reasoning
- find papers on in-context learning
- introductory book to get started with LLMs

## When to choose
- you want a comprehensive, curated reading list and roadmap for LLM research
- you are a student or researcher entering the LLM field
- you need a citable survey covering LLMs up to recent reasoning models

## When to avoid
- you need runnable LLM software or training code
- you want a hands-on tutorial with code exercises rather than a paper collection

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, nlp, llm-training, prompt-engineering
- domain: large-language-models, tutorials, artificial-intelligence
- platform: python
- tags: survey-paper, llm, chain-of-thought, rlhf, instruction-tuning, pre-training, academic-resource, paper-collection, natural-language-processing

## Member repositories
- RUCAIBox/LLMSurvey (main) score 35

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:52.035146+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:14:16.517540+00:00, confidence not recorded.
  - readme: https://github.com/RUCAIBox/LLMSurvey (fetched 2026-08-28T04:10:52.035146+00:00, sha c075d5a10d80)
  - homepage: https://arxiv.org/abs/2303.18223 (fetched 2026-08-29T08:11:51.998838+00:00, sha 241ff5afc38f)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:11:52.008720+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:11:52.012958+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:11:52.015105+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:11:52.010844+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.