{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YTFSJT3YA232UQ4WXV6HI2S5HP","short_pith_number":"pith:YTFSJT3Y","schema_version":"1.0","canonical_sha256":"c4cb24cf7806b7aa4396bd7c746a5d3bc6cf7a2b44f5b6b40fb85083f1db6a8b","source":{"kind":"arxiv","id":"2410.00863","version":1},"attestation_state":"computed","paper":{"title":"On the Implications of Verbose LLM Outputs: A Case Study in Translation Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Colin Cherry, Eleftheria Briakou, Markus Freitag, Zhongtao Liu","submitted_at":"2024-10-01T16:59:01Z","abstract_excerpt":"This paper investigates the impact of verbose LLM translations on evaluation. We first demonstrate the prevalence of this behavior across several LLM outputs drawn from the WMT 2024 general shared task on machine translation. We then identify the primary triggers of verbosity, including safety, copyright concerns, and insufficient context in short input queries. Finally, we show that ignoring this behavior unfairly penalizes more verbose LLMs according to both automatic and human evaluations, highlighting the need to address this issue for more accurate future evaluations."},"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":"2410.00863","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-01T16:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"f13b168ff17ad1b960c32e9ca6e5c94dea3f8baa71e3f75fb9d44d5464bd4733","abstract_canon_sha256":"d4c1722c9a3ed66b678aff471a40bb1251f325c7b87e3e5c0ae9e18a9a8e4e37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:23.880323Z","signature_b64":"aw+9QPHn4w/Lbcy/9jjIe8IiAqxeR6UtrCCA4G10ouxA4OaySEnzFRqiktWYpTkriIdOQcJd4shKQGE7czHPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4cb24cf7806b7aa4396bd7c746a5d3bc6cf7a2b44f5b6b40fb85083f1db6a8b","last_reissued_at":"2026-07-05T09:14:23.879818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:23.879818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Implications of Verbose LLM Outputs: A Case Study in Translation Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Colin Cherry, Eleftheria Briakou, Markus Freitag, Zhongtao Liu","submitted_at":"2024-10-01T16:59:01Z","abstract_excerpt":"This paper investigates the impact of verbose LLM translations on evaluation. We first demonstrate the prevalence of this behavior across several LLM outputs drawn from the WMT 2024 general shared task on machine translation. We then identify the primary triggers of verbosity, including safety, copyright concerns, and insufficient context in short input queries. Finally, we show that ignoring this behavior unfairly penalizes more verbose LLMs according to both automatic and human evaluations, highlighting the need to address this issue for more accurate future evaluations."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00863","kind":"arxiv","version":1},"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/2410.00863/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":"2410.00863","created_at":"2026-07-05T09:14:23.879877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00863v1","created_at":"2026-07-05T09:14:23.879877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00863","created_at":"2026-07-05T09:14:23.879877+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTFSJT3YA232","created_at":"2026-07-05T09:14:23.879877+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTFSJT3YA232UQ4W","created_at":"2026-07-05T09:14:23.879877+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTFSJT3Y","created_at":"2026-07-05T09:14:23.879877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.01919","citing_title":"Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation","ref_index":178,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12613","citing_title":"Creating Group Rules with AI: Human-AI Collaboration in WhatsApp Moderation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTFSJT3YA232UQ4WXV6HI2S5HP","json":"https://pith.science/pith/YTFSJT3YA232UQ4WXV6HI2S5HP.json","graph_json":"https://pith.science/api/pith-number/YTFSJT3YA232UQ4WXV6HI2S5HP/graph.json","events_json":"https://pith.science/api/pith-number/YTFSJT3YA232UQ4WXV6HI2S5HP/events.json","paper":"https://pith.science/paper/YTFSJT3Y"},"agent_actions":{"view_html":"https://pith.science/pith/YTFSJT3YA232UQ4WXV6HI2S5HP","download_json":"https://pith.science/pith/YTFSJT3YA232UQ4WXV6HI2S5HP.json","view_paper":"https://pith.science/paper/YTFSJT3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00863&json=true","fetch_graph":"https://pith.science/api/pith-number/YTFSJT3YA232UQ4WXV6HI2S5HP/graph.json","fetch_events":"https://pith.science/api/pith-number/YTFSJT3YA232UQ4WXV6HI2S5HP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTFSJT3YA232UQ4WXV6HI2S5HP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTFSJT3YA232UQ4WXV6HI2S5HP/action/storage_attestation","attest_author":"https://pith.science/pith/YTFSJT3YA232UQ4WXV6HI2S5HP/action/author_attestation","sign_citation":"https://pith.science/pith/YTFSJT3YA232UQ4WXV6HI2S5HP/action/citation_signature","submit_replication":"https://pith.science/pith/YTFSJT3YA232UQ4WXV6HI2S5HP/action/replication_record"}},"created_at":"2026-07-05T09:14:23.879877+00:00","updated_at":"2026-07-05T09:14:23.879877+00:00"}