{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LNHMUG26CGVS6IHCLIN6FCCEEJ","short_pith_number":"pith:LNHMUG26","schema_version":"1.0","canonical_sha256":"5b4eca1b5e11ab2f20e25a1be288442255d30d45d260ca52316dfc1e3651bab2","source":{"kind":"arxiv","id":"2307.07889","version":3},"attestation_state":"computed","paper":{"title":"LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adian Liusie, Mark J. F. Gales, Potsawee Manakul","submitted_at":"2023-07-15T22:02:12Z","abstract_excerpt":"Current developments in large language models (LLMs) have enabled impressive zero-shot capabilities across various natural language tasks. An interesting application of these systems is in the automated assessment of natural language generation (NLG), a highly challenging area with great practical benefit. In this paper, we explore two options for exploiting the emergent abilities of LLMs for zero-shot NLG assessment: absolute score prediction, and comparative assessment which uses relative comparisons between pairs of candidates. Though comparative assessment has not been extensively studied "},"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":"2307.07889","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-15T22:02:12Z","cross_cats_sorted":[],"title_canon_sha256":"e3cada5d2c4f530201d8e5298b81670289974b1138485707f8ed8b170ec0adc1","abstract_canon_sha256":"001b76e1b5fadc5cba2bfc2fc69b1edcf6ac5bf56b089fbb1170b4ada2d0ed3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:41.463111Z","signature_b64":"CoYhYwiVSSEMUfYI2nbvCMSG0VbEi+cnk3NZJ3frZDrj9FMIFM12I9Pq2whjU+jJHbTHjLGSlZ+INvFjaG3/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b4eca1b5e11ab2f20e25a1be288442255d30d45d260ca52316dfc1e3651bab2","last_reissued_at":"2026-07-05T07:41:41.462693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:41.462693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adian Liusie, Mark J. F. Gales, Potsawee Manakul","submitted_at":"2023-07-15T22:02:12Z","abstract_excerpt":"Current developments in large language models (LLMs) have enabled impressive zero-shot capabilities across various natural language tasks. An interesting application of these systems is in the automated assessment of natural language generation (NLG), a highly challenging area with great practical benefit. In this paper, we explore two options for exploiting the emergent abilities of LLMs for zero-shot NLG assessment: absolute score prediction, and comparative assessment which uses relative comparisons between pairs of candidates. Though comparative assessment has not been extensively studied "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07889","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/2307.07889/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":"2307.07889","created_at":"2026-07-05T07:41:41.462751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07889v3","created_at":"2026-07-05T07:41:41.462751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07889","created_at":"2026-07-05T07:41:41.462751+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNHMUG26CGVS","created_at":"2026-07-05T07:41:41.462751+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNHMUG26CGVS6IHC","created_at":"2026-07-05T07:41:41.462751+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNHMUG26","created_at":"2026-07-05T07:41:41.462751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05443","citing_title":"MIRAI: Prediction and Generation of High-Impact Academic Research","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27446","citing_title":"Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27316","citing_title":"LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2603.14410","citing_title":"BiT-MCTS: A Theme-based Bidirectional MCTS Approach to Chinese Fiction Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18835","citing_title":"Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNHMUG26CGVS6IHCLIN6FCCEEJ","json":"https://pith.science/pith/LNHMUG26CGVS6IHCLIN6FCCEEJ.json","graph_json":"https://pith.science/api/pith-number/LNHMUG26CGVS6IHCLIN6FCCEEJ/graph.json","events_json":"https://pith.science/api/pith-number/LNHMUG26CGVS6IHCLIN6FCCEEJ/events.json","paper":"https://pith.science/paper/LNHMUG26"},"agent_actions":{"view_html":"https://pith.science/pith/LNHMUG26CGVS6IHCLIN6FCCEEJ","download_json":"https://pith.science/pith/LNHMUG26CGVS6IHCLIN6FCCEEJ.json","view_paper":"https://pith.science/paper/LNHMUG26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07889&json=true","fetch_graph":"https://pith.science/api/pith-number/LNHMUG26CGVS6IHCLIN6FCCEEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LNHMUG26CGVS6IHCLIN6FCCEEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNHMUG26CGVS6IHCLIN6FCCEEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNHMUG26CGVS6IHCLIN6FCCEEJ/action/storage_attestation","attest_author":"https://pith.science/pith/LNHMUG26CGVS6IHCLIN6FCCEEJ/action/author_attestation","sign_citation":"https://pith.science/pith/LNHMUG26CGVS6IHCLIN6FCCEEJ/action/citation_signature","submit_replication":"https://pith.science/pith/LNHMUG26CGVS6IHCLIN6FCCEEJ/action/replication_record"}},"created_at":"2026-07-05T07:41:41.462751+00:00","updated_at":"2026-07-05T07:41:41.462751+00:00"}