{"adoption": {"forks": 101, "observed_at": "2026-08-28T04:05:10.858538+00:00", "stars": 1609}, "canonical_url": "https://ross.abutalabs.com/products/llm-eval-survey", "card": {"archived": false, "artifact_type": "learning-resource", "description": "The official GitHub page for the survey paper \"A Survey on Evaluation of Large Language Models\".", "domain": ["large-language-models", "artificial-intelligence", "tutorials", "awesome-lists"], "enriched": true, "function": ["documentation", "benchmarking"], "health_score": 77, "homepage": "https://arxiv.org/abs/2307.03109", "language": null, "license": null, "license_family": "other", "maturity": "active", "member_repos": ["MLGroupJLU/LLM-eval-survey"], "name": "MLGroupJLU/LLM-eval-survey", "platform": [], "pushed_at": "2026-08-01T05:43:40+00:00", "repo": "MLGroupJLU/LLM-eval-survey", "stars": 1609, "tags": ["survey-paper", "llm-evaluation", "benchmarks", "paper-collection", "reading-list", "web-server"], "topics": ["benchmark", "evaluation", "large-language-models", "llm", "llms", "model-assessment"], "urls": [], "use_cases": ["find papers on evaluating large language models", "survey of LLM benchmarks and evaluation methods", "learn how to assess LLM trustworthiness and robustness", "find benchmarks for medical or agent applications of LLMs", "keep up to date with new LLM evaluation research", "background reading for designing an LLM evaluation strategy"], "what_it_is": "The official repository accompanying the survey paper 'A Survey on Evaluation of Large Language Models', curating papers and resources on LLM evaluation. It organizes research by what to evaluate (NLP, robustness, ethics, science, medicine, agents) and where/how to evaluate (benchmarks and methods).", "when_to_avoid": ["you need runnable evaluation code or a tool rather than a paper collection", "you need a single benchmark dataset to execute", "you require licensed software with support guarantees"], "when_to_choose": ["you need a curated, organized reading list of LLM evaluation papers", "you are writing a related-work section on LLM assessment", "you want to discover benchmarks across many task domains"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llm-eval-survey", "repo": "MLGroupJLU/LLM-eval-survey", "role": "main", "score": 71}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:51:15.524786+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e9679b06e1a8b8609bd3362fda5109e86ed9a90d0dec4130aea54cc6b9001c9", "fetched_at": "2026-08-28T04:05:10.858538+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MLGroupJLU/LLM-eval-survey"}, {"content_hash": "73a51ff639988754ea9b2bf77cc07662b680668c0ef3806f093d2940d76ef1ce", "fetched_at": "2026-08-29T11:23:46.513894+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2307.03109"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:23:46.516804+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:23:46.520797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:23:46.523012+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:23:46.518923+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:51:15.524786+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e9679b06e1a8b8609bd3362fda5109e86ed9a90d0dec4130aea54cc6b9001c9", "fetched_at": "2026-08-28T04:05:10.858538+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MLGroupJLU/LLM-eval-survey"}, {"content_hash": "73a51ff639988754ea9b2bf77cc07662b680668c0ef3806f093d2940d76ef1ce", "fetched_at": "2026-08-29T11:23:46.513894+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2307.03109"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:23:46.516804+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:23:46.520797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:23:46.523012+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:23:46.518923+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:51:15.524786+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e9679b06e1a8b8609bd3362fda5109e86ed9a90d0dec4130aea54cc6b9001c9", "fetched_at": "2026-08-28T04:05:10.858538+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MLGroupJLU/LLM-eval-survey"}, {"content_hash": "73a51ff639988754ea9b2bf77cc07662b680668c0ef3806f093d2940d76ef1ce", "fetched_at": "2026-08-29T11:23:46.513894+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2307.03109"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:23:46.516804+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:23:46.520797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:23:46.523012+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:23:46.518923+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:51:15.524786+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e9679b06e1a8b8609bd3362fda5109e86ed9a90d0dec4130aea54cc6b9001c9", "fetched_at": "2026-08-28T04:05:10.858538+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MLGroupJLU/LLM-eval-survey"}, {"content_hash": "73a51ff639988754ea9b2bf77cc07662b680668c0ef3806f093d2940d76ef1ce", "fetched_at": "2026-08-29T11:23:46.513894+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2307.03109"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:23:46.516804+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:23:46.520797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:23:46.523012+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:23:46.518923+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:51:15.524786+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e9679b06e1a8b8609bd3362fda5109e86ed9a90d0dec4130aea54cc6b9001c9", "fetched_at": "2026-08-28T04:05:10.858538+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MLGroupJLU/LLM-eval-survey"}, {"content_hash": "73a51ff639988754ea9b2bf77cc07662b680668c0ef3806f093d2940d76ef1ce", "fetched_at": "2026-08-29T11:23:46.513894+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2307.03109"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:23:46.516804+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:23:46.520797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:23:46.523012+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:23:46.518923+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:51:15.524786+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e9679b06e1a8b8609bd3362fda5109e86ed9a90d0dec4130aea54cc6b9001c9", "fetched_at": "2026-08-28T04:05:10.858538+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MLGroupJLU/LLM-eval-survey"}, {"content_hash": "73a51ff639988754ea9b2bf77cc07662b680668c0ef3806f093d2940d76ef1ce", "fetched_at": "2026-08-29T11:23:46.513894+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2307.03109"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:23:46.516804+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:23:46.520797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:23:46.523012+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:23:46.518923+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.858538+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:51:15.524786+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e9679b06e1a8b8609bd3362fda5109e86ed9a90d0dec4130aea54cc6b9001c9", "fetched_at": "2026-08-28T04:05:10.858538+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MLGroupJLU/LLM-eval-survey"}, {"content_hash": "73a51ff639988754ea9b2bf77cc07662b680668c0ef3806f093d2940d76ef1ce", "fetched_at": "2026-08-29T11:23:46.513894+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2307.03109"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:23:46.516804+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:23:46.520797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:23:46.523012+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:23:46.518923+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:51:15.524786+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e9679b06e1a8b8609bd3362fda5109e86ed9a90d0dec4130aea54cc6b9001c9", "fetched_at": "2026-08-28T04:05:10.858538+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MLGroupJLU/LLM-eval-survey"}, {"content_hash": "73a51ff639988754ea9b2bf77cc07662b680668c0ef3806f093d2940d76ef1ce", "fetched_at": "2026-08-29T11:23:46.513894+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2307.03109"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:23:46.516804+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:23:46.520797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:23:46.523012+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:23:46.518923+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:51:15.524786+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e9679b06e1a8b8609bd3362fda5109e86ed9a90d0dec4130aea54cc6b9001c9", "fetched_at": "2026-08-28T04:05:10.858538+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MLGroupJLU/LLM-eval-survey"}, {"content_hash": "73a51ff639988754ea9b2bf77cc07662b680668c0ef3806f093d2940d76ef1ce", "fetched_at": "2026-08-29T11:23:46.513894+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2307.03109"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:23:46.516804+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:23:46.520797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:23:46.523012+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:23:46.518923+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:51:15.524786+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4e9679b06e1a8b8609bd3362fda5109e86ed9a90d0dec4130aea54cc6b9001c9", "fetched_at": "2026-08-28T04:05:10.858538+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MLGroupJLU/LLM-eval-survey"}, {"content_hash": "73a51ff639988754ea9b2bf77cc07662b680668c0ef3806f093d2940d76ef1ce", "fetched_at": "2026-08-29T11:23:46.513894+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2307.03109"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:23:46.516804+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:23:46.520797+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:23:46.523012+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:23:46.518923+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 95, "longevity": 82, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1158, "days_push": 32, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 71, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}