{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:43DE4JPF2RMKXAUW4OUAL3WVRH","short_pith_number":"pith:43DE4JPF","schema_version":"1.0","canonical_sha256":"e6c64e25e5d458ab8296e3a805eed589ef82bb7d4b6fb8bfb86a1329b8badb84","source":{"kind":"arxiv","id":"2407.05216","version":2},"attestation_state":"computed","paper":{"title":"Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng-Han Chiang, Chienchou Yang, Chun-Yi Kuan, Hung-yi Lee, Wei-Chih Chen","submitted_at":"2024-07-07T00:17:24Z","abstract_excerpt":"Using large language models (LLMs) for automatic evaluation has become an important evaluation method in NLP research. However, it is unclear whether these LLM-based evaluators can be applied in real-world classrooms to assess student assignments. This empirical report shares how we use GPT-4 as an automatic assignment evaluator in a university course with 1,028 students. Based on student responses, we find that LLM-based assignment evaluators are generally acceptable to students when students have free access to these LLM-based evaluators. However, students also noted that the LLM sometimes f"},"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":"2407.05216","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-07T00:17:24Z","cross_cats_sorted":[],"title_canon_sha256":"04d0efd7c7ef0711a52f657261967a822dda15526104052f38d7022488c175e2","abstract_canon_sha256":"84fd6ad64a6399db954730f98893705851773c73cc9a7fcbd54c7b547ed882dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:01.488303Z","signature_b64":"tpsdQfSaZU/2jr1994Uri+VC6DTLpliUSzxb6/8BAGacUOa/B3ByOI7OmjrhwmoWH1dZWnDJjHfTiLSnooPtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6c64e25e5d458ab8296e3a805eed589ef82bb7d4b6fb8bfb86a1329b8badb84","last_reissued_at":"2026-07-05T09:10:01.487836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:01.487836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng-Han Chiang, Chienchou Yang, Chun-Yi Kuan, Hung-yi Lee, Wei-Chih Chen","submitted_at":"2024-07-07T00:17:24Z","abstract_excerpt":"Using large language models (LLMs) for automatic evaluation has become an important evaluation method in NLP research. However, it is unclear whether these LLM-based evaluators can be applied in real-world classrooms to assess student assignments. This empirical report shares how we use GPT-4 as an automatic assignment evaluator in a university course with 1,028 students. Based on student responses, we find that LLM-based assignment evaluators are generally acceptable to students when students have free access to these LLM-based evaluators. However, students also noted that the LLM sometimes f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05216","kind":"arxiv","version":2},"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/2407.05216/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":"2407.05216","created_at":"2026-07-05T09:10:01.487895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05216v2","created_at":"2026-07-05T09:10:01.487895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05216","created_at":"2026-07-05T09:10:01.487895+00:00"},{"alias_kind":"pith_short_12","alias_value":"43DE4JPF2RMK","created_at":"2026-07-05T09:10:01.487895+00:00"},{"alias_kind":"pith_short_16","alias_value":"43DE4JPF2RMKXAUW","created_at":"2026-07-05T09:10:01.487895+00:00"},{"alias_kind":"pith_short_8","alias_value":"43DE4JPF","created_at":"2026-07-05T09:10:01.487895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43DE4JPF2RMKXAUW4OUAL3WVRH","json":"https://pith.science/pith/43DE4JPF2RMKXAUW4OUAL3WVRH.json","graph_json":"https://pith.science/api/pith-number/43DE4JPF2RMKXAUW4OUAL3WVRH/graph.json","events_json":"https://pith.science/api/pith-number/43DE4JPF2RMKXAUW4OUAL3WVRH/events.json","paper":"https://pith.science/paper/43DE4JPF"},"agent_actions":{"view_html":"https://pith.science/pith/43DE4JPF2RMKXAUW4OUAL3WVRH","download_json":"https://pith.science/pith/43DE4JPF2RMKXAUW4OUAL3WVRH.json","view_paper":"https://pith.science/paper/43DE4JPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05216&json=true","fetch_graph":"https://pith.science/api/pith-number/43DE4JPF2RMKXAUW4OUAL3WVRH/graph.json","fetch_events":"https://pith.science/api/pith-number/43DE4JPF2RMKXAUW4OUAL3WVRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43DE4JPF2RMKXAUW4OUAL3WVRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43DE4JPF2RMKXAUW4OUAL3WVRH/action/storage_attestation","attest_author":"https://pith.science/pith/43DE4JPF2RMKXAUW4OUAL3WVRH/action/author_attestation","sign_citation":"https://pith.science/pith/43DE4JPF2RMKXAUW4OUAL3WVRH/action/citation_signature","submit_replication":"https://pith.science/pith/43DE4JPF2RMKXAUW4OUAL3WVRH/action/replication_record"}},"created_at":"2026-07-05T09:10:01.487895+00:00","updated_at":"2026-07-05T09:10:01.487895+00:00"}