# ydyjya/Awesome-LLM-Safety

A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights into the safety implications, challenges, and advancements surrounding these powerful models.

Repository: https://github.com/ydyjya/Awesome-LLM-Safety
Canonical: https://ross.abutalabs.com/products/awesome-llm-safety
Language: HTML
License Family: other
Last push: 2026-07-12T12:25:53+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 35, longevity 74
- inputs: {"age_days": 1039, "days_push": 52, "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 1901, forks 118 (observed 2026-08-28T04:05:51.641454+00:00)

## What it is
A curated awesome-list of papers, tutorials, talks, and articles on Large Language Model safety, organized into subtopics with brief introductions. It serves as a research navigation resource for beginners and experienced researchers tracking the LLM safety field.

## Use cases
- find papers on llm safety and alignment
- survey recent research on jailbreaks and prompt injection
- get started learning about large language model safety
- track latest llm safety papers from conferences
- find tutorials and talks on ai safety
- research red teaming techniques for llms

## When to choose
- you need a broad, continuously updated survey of LLM safety literature
- you are a beginner wanting a structured entry point into the field
- you are a researcher looking for conference paper collections on safety subtopics

## When to avoid
- you need runnable safety tooling or code rather than a reading list
- you need a single authoritative reference rather than a curated link collection

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, developer-tools
- domain: large-language-models, artificial-intelligence, security, tutorials, awesome-lists
- platform: -
- tags: awesome-list, llm-safety, curated-papers, research-resources, ai-alignment, red-teaming, web-server

## Member repositories
- ydyjya/Awesome-LLM-Safety (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:51.641454+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 2026-08-30T03:11:58.000707+00:00, confidence not recorded.
  - readme: https://github.com/ydyjya/Awesome-LLM-Safety (fetched 2026-08-28T04:05:51.641454+00:00, sha 4c4dc2f7eff7)
- Data as of 2026-08-30T08:39:29.467469+00:00.