# thunlp/PLMpapers

Must-read Papers on pre-trained language models.

Repository: https://github.com/thunlp/PLMpapers
Canonical: https://ross.abutalabs.com/products/plmpapers
License: MIT
License Family: permissive
Last push: 2022-11-06T09:37:38+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2536, "days_push": 1396, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3359, forks 431 (observed 2026-08-28T04:07:58.024783+00:00)

## What it is
A curated reading list of must-read papers on pre-trained language models (PLMs), with a family diagram showing relationships between models like BERT, GPT, and ELMo. It also links to open PLMs released by the THUNLP group and a survey paper.

## Use cases
- find must-read papers on pre-trained language models
- learn the history and evolution of BERT and GPT style models
- get an overview of PLM research for a literature review
- find a diagram of how pre-trained language models relate to each other
- prepare a presentation on transformer language models
- find survey papers on pre-trained models in NLP

## When to choose
- you want a curated, organized paper list on PLMs rather than searching manually
- you need a visual map of the PLM model family for study or slides
- you are starting research or coursework on pre-trained language models

## When to avoid
- you need runnable code or model implementations rather than paper references
- you need up-to-date coverage of recent LLM papers, as the list was last updated in 2022
- you want tutorials or courses rather than academic papers

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: nlp, machine-learning, documentation
- domain: large-language-models, tutorials, awesome-lists
- platform: cross-platform
- tags: paper-list, pre-trained-language-models, survey, reading-list, transformers, natural-language-processing

## Member repositories
- thunlp/PLMpapers (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:58.024783+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 2026-08-29T18:40:53.573297+00:00, confidence not recorded.
  - readme: https://github.com/thunlp/PLMpapers (fetched 2026-08-28T04:07:58.024783+00:00, sha 3a3ee178a8fd)
- Data as of 2026-08-30T08:39:29.467469+00:00.