{"adoption": {"forks": 89, "observed_at": "2026-08-28T04:04:00.781817+00:00", "stars": 1214}, "canonical_url": "https://ross.abutalabs.com/products/safety-prompts", "card": {"archived": false, "artifact_type": "dataset", "description": "Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。", "domain": ["large-language-models", "security", "artificial-intelligence"], "enriched": true, "function": ["prompt-engineering", "machine-learning", "llm-training", "security"], "health_score": 20, "homepage": "http://coai.cs.tsinghua.edu.cn/leaderboard/", "language": null, "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["thu-coai/Safety-Prompts"], "name": "thu-coai/Safety-Prompts", "platform": ["python", "cross-platform"], "pushed_at": "2024-02-27T08:42:12+00:00", "repo": "thu-coai/Safety-Prompts", "stars": 1214, "tags": ["llm-safety", "chinese-language", "safety-evaluation", "instruction-attacks", "alignment", "benchmark", "fine-tuning-data", "natural-language-processing"], "topics": ["attack-defense", "chatgpt", "instruction", "llm", "prompt", "prompt-engineering", "safety", "chinese-language"], "urls": [], "use_cases": ["evaluate the safety of a Chinese LLM", "fine-tune a model to refuse unsafe requests", "test robustness against prompt injection and jailbreak attacks", "align model outputs with human values", "build a safety benchmark for Chinese chatbots", "research instruction attack categories like goal hijacking and prompt leaking"], "what_it_is": "A dataset of 100k Chinese safety prompts with ChatGPT responses covering typical unsafe scenarios and instruction attacks, for evaluating and improving LLM safety. It accompanies the paper 'Safety Assessment of Chinese Large Language Models' from Tsinghua's thu-coai group.", "when_to_avoid": ["you need English-language safety data", "you want multiple-choice safety benchmarking - use the authors' SafetyBench instead", "you need a ready-made safety detector - use the authors' ShieldLM instead"], "when_to_choose": ["you need large-scale Chinese-language safety training or evaluation data", "you want to test LLM robustness against Chinese instruction attacks", "you are aligning a Chinese chatbot with safety norms"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/safety-prompts", "repo": "thu-coai/Safety-Prompts", "role": "main", "score": 30}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:17:31.295691+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c5a6627378692531257f43041ea0bec35054f0682b4133a583fd8baf4eb61e20", "fetched_at": "2026-08-28T04:04:00.781817+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-coai/Safety-Prompts"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:17:31.295691+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c5a6627378692531257f43041ea0bec35054f0682b4133a583fd8baf4eb61e20", "fetched_at": "2026-08-28T04:04:00.781817+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-coai/Safety-Prompts"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:17:31.295691+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c5a6627378692531257f43041ea0bec35054f0682b4133a583fd8baf4eb61e20", "fetched_at": "2026-08-28T04:04:00.781817+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-coai/Safety-Prompts"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:17:31.295691+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c5a6627378692531257f43041ea0bec35054f0682b4133a583fd8baf4eb61e20", "fetched_at": "2026-08-28T04:04:00.781817+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-coai/Safety-Prompts"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:17:31.295691+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c5a6627378692531257f43041ea0bec35054f0682b4133a583fd8baf4eb61e20", "fetched_at": "2026-08-28T04:04:00.781817+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-coai/Safety-Prompts"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:17:31.295691+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c5a6627378692531257f43041ea0bec35054f0682b4133a583fd8baf4eb61e20", "fetched_at": "2026-08-28T04:04:00.781817+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-coai/Safety-Prompts"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.781817+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:17:31.295691+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c5a6627378692531257f43041ea0bec35054f0682b4133a583fd8baf4eb61e20", "fetched_at": "2026-08-28T04:04:00.781817+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-coai/Safety-Prompts"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:17:31.295691+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c5a6627378692531257f43041ea0bec35054f0682b4133a583fd8baf4eb61e20", "fetched_at": "2026-08-28T04:04:00.781817+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-coai/Safety-Prompts"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:17:31.295691+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c5a6627378692531257f43041ea0bec35054f0682b4133a583fd8baf4eb61e20", "fetched_at": "2026-08-28T04:04:00.781817+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-coai/Safety-Prompts"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:17:31.295691+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c5a6627378692531257f43041ea0bec35054f0682b4133a583fd8baf4eb61e20", "fetched_at": "2026-08-28T04:04:00.781817+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thu-coai/Safety-Prompts"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 88, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1233, "days_push": 918, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 30, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}