{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CLJQQXGFKWESVGHXOVZ44X34IG","short_pith_number":"pith:CLJQQXGF","schema_version":"1.0","canonical_sha256":"12d3085cc555892a98f77573ce5f7c41a7b39e00b3e28bca38d327976f68eaca","source":{"kind":"arxiv","id":"2304.00723","version":3},"attestation_state":"computed","paper":{"title":"Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyun Jiang, Ruifeng Xu, Rui Wang, Shuming Shi, Yi Chen","submitted_at":"2023-04-03T05:29:58Z","abstract_excerpt":"Evaluating the quality of generated text is a challenging task in NLP, due to the inherent complexity and diversity of text. Recently, large language models (LLMs) have garnered significant attention due to their impressive performance in various tasks. Therefore, we present this paper to investigate the effectiveness of LLMs, especially ChatGPT, and explore ways to optimize their use in assessing text quality. We compared three kinds of reference-free evaluation methods. The experimental results prove that ChatGPT is capable of evaluating text quality effectively from various perspectives wit"},"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":"2304.00723","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-03T05:29:58Z","cross_cats_sorted":[],"title_canon_sha256":"7e97c77e79bb1972a12885be826db4bbdbf608f060aa4a129f468d918209a4b3","abstract_canon_sha256":"b348cd4a77e35b71c681705a92c9d6214c6df073afe1c4a97df55fd8f2548c4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:24.160193Z","signature_b64":"iV7EJPwKZSP4w1ltBAiSpq6+i2td0EPYL3oxD0Iwef8uFHeXfYS0efjNVmZU4yBiWY24c7mxvuVv1kfq0bSRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12d3085cc555892a98f77573ce5f7c41a7b39e00b3e28bca38d327976f68eaca","last_reissued_at":"2026-07-05T06:51:24.159684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:24.159684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyun Jiang, Ruifeng Xu, Rui Wang, Shuming Shi, Yi Chen","submitted_at":"2023-04-03T05:29:58Z","abstract_excerpt":"Evaluating the quality of generated text is a challenging task in NLP, due to the inherent complexity and diversity of text. Recently, large language models (LLMs) have garnered significant attention due to their impressive performance in various tasks. Therefore, we present this paper to investigate the effectiveness of LLMs, especially ChatGPT, and explore ways to optimize their use in assessing text quality. We compared three kinds of reference-free evaluation methods. The experimental results prove that ChatGPT is capable of evaluating text quality effectively from various perspectives wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00723","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/2304.00723/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":"2304.00723","created_at":"2026-07-05T06:51:24.159747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00723v3","created_at":"2026-07-05T06:51:24.159747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00723","created_at":"2026-07-05T06:51:24.159747+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLJQQXGFKWES","created_at":"2026-07-05T06:51:24.159747+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLJQQXGFKWESVGHX","created_at":"2026-07-05T06:51:24.159747+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLJQQXGF","created_at":"2026-07-05T06:51:24.159747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21350","citing_title":"Factored Causal Representation Learning for Robust Reward Modeling in RLHF","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04305","citing_title":"SWAN: Semantic Watermarking with Abstract Meaning Representation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06987","citing_title":"Response Time Enhances Alignment with Heterogeneous Preferences","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2305.18290","citing_title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06666","citing_title":"A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLJQQXGFKWESVGHXOVZ44X34IG","json":"https://pith.science/pith/CLJQQXGFKWESVGHXOVZ44X34IG.json","graph_json":"https://pith.science/api/pith-number/CLJQQXGFKWESVGHXOVZ44X34IG/graph.json","events_json":"https://pith.science/api/pith-number/CLJQQXGFKWESVGHXOVZ44X34IG/events.json","paper":"https://pith.science/paper/CLJQQXGF"},"agent_actions":{"view_html":"https://pith.science/pith/CLJQQXGFKWESVGHXOVZ44X34IG","download_json":"https://pith.science/pith/CLJQQXGFKWESVGHXOVZ44X34IG.json","view_paper":"https://pith.science/paper/CLJQQXGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00723&json=true","fetch_graph":"https://pith.science/api/pith-number/CLJQQXGFKWESVGHXOVZ44X34IG/graph.json","fetch_events":"https://pith.science/api/pith-number/CLJQQXGFKWESVGHXOVZ44X34IG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLJQQXGFKWESVGHXOVZ44X34IG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLJQQXGFKWESVGHXOVZ44X34IG/action/storage_attestation","attest_author":"https://pith.science/pith/CLJQQXGFKWESVGHXOVZ44X34IG/action/author_attestation","sign_citation":"https://pith.science/pith/CLJQQXGFKWESVGHXOVZ44X34IG/action/citation_signature","submit_replication":"https://pith.science/pith/CLJQQXGFKWESVGHXOVZ44X34IG/action/replication_record"}},"created_at":"2026-07-05T06:51:24.159747+00:00","updated_at":"2026-07-05T06:51:24.159747+00:00"}