{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:54726C2YGUFEP6YRJR5JPFY3S6","short_pith_number":"pith:54726C2Y","schema_version":"1.0","canonical_sha256":"ef3faf0b58350a47fb114c7a97971b97acd4205a63b82ce0fb2225c722bce901","source":{"kind":"arxiv","id":"2312.07910","version":3},"attestation_state":"computed","paper":{"title":"PromptBench: A Unified Library for Evaluation of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Hao Chen, Jindong Wang, Kaijie Zhu, Qinlin Zhao, Xing Xie","submitted_at":"2023-12-13T05:58:34Z","abstract_excerpt":"The evaluation of large language models (LLMs) is crucial to assess their performance and mitigate potential security risks. In this paper, we introduce PromptBench, a unified library to evaluate LLMs. It consists of several key components that are easily used and extended by researchers: prompt construction, prompt engineering, dataset and model loading, adversarial prompt attack, dynamic evaluation protocols, and analysis tools. PromptBench is designed to be an open, general, and flexible codebase for research purposes that can facilitate original study in creating new benchmarks, deploying "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.07910","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T05:58:34Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e783552ab201504d9745a73dedc5553b2ae90f464283137648e6ed560f5def13","abstract_canon_sha256":"7870982ca6c95a5a6835d373784ae5028077729331f098ebf7268780d82a7b9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:58.417783Z","signature_b64":"wVmN1eI5i1Mcq3oPKpanVpeUzM3O54tG1YQDMk//iVeeViUXTIgE6AFnPqxkAJG8sM3pbqHCEUFn1qB3ICjiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef3faf0b58350a47fb114c7a97971b97acd4205a63b82ce0fb2225c722bce901","last_reissued_at":"2026-07-05T08:56:58.417340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:58.417340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptBench: A Unified Library for Evaluation of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Hao Chen, Jindong Wang, Kaijie Zhu, Qinlin Zhao, Xing Xie","submitted_at":"2023-12-13T05:58:34Z","abstract_excerpt":"The evaluation of large language models (LLMs) is crucial to assess their performance and mitigate potential security risks. In this paper, we introduce PromptBench, a unified library to evaluate LLMs. It consists of several key components that are easily used and extended by researchers: prompt construction, prompt engineering, dataset and model loading, adversarial prompt attack, dynamic evaluation protocols, and analysis tools. PromptBench is designed to be an open, general, and flexible codebase for research purposes that can facilitate original study in creating new benchmarks, deploying "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07910","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.07910/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.07910","created_at":"2026-07-05T08:56:58.417403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07910v3","created_at":"2026-07-05T08:56:58.417403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07910","created_at":"2026-07-05T08:56:58.417403+00:00"},{"alias_kind":"pith_short_12","alias_value":"54726C2YGUFE","created_at":"2026-07-05T08:56:58.417403+00:00"},{"alias_kind":"pith_short_16","alias_value":"54726C2YGUFEP6YR","created_at":"2026-07-05T08:56:58.417403+00:00"},{"alias_kind":"pith_short_8","alias_value":"54726C2Y","created_at":"2026-07-05T08:56:58.417403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22797","citing_title":"Measuring Behavior Portability in Large Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13510","citing_title":"Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2404.01318","citing_title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6","json":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6.json","graph_json":"https://pith.science/api/pith-number/54726C2YGUFEP6YRJR5JPFY3S6/graph.json","events_json":"https://pith.science/api/pith-number/54726C2YGUFEP6YRJR5JPFY3S6/events.json","paper":"https://pith.science/paper/54726C2Y"},"agent_actions":{"view_html":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6","download_json":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6.json","view_paper":"https://pith.science/paper/54726C2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07910&json=true","fetch_graph":"https://pith.science/api/pith-number/54726C2YGUFEP6YRJR5JPFY3S6/graph.json","fetch_events":"https://pith.science/api/pith-number/54726C2YGUFEP6YRJR5JPFY3S6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6/action/storage_attestation","attest_author":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6/action/author_attestation","sign_citation":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6/action/citation_signature","submit_replication":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6/action/replication_record"}},"created_at":"2026-07-05T08:56:58.417403+00:00","updated_at":"2026-07-05T08:56:58.417403+00:00"}