{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SB7XE7OB5343KW36RVOIMDNR4K","short_pith_number":"pith:SB7XE7OB","schema_version":"1.0","canonical_sha256":"907f727dc1eef9b55b7e8d5c860db1e29e3adcc22f28a0533f21ab5f1ba4a858","source":{"kind":"arxiv","id":"2412.16120","version":1},"attestation_state":"computed","paper":{"title":"PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metrics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniil Larionov, Steffen Eger","submitted_at":"2024-12-20T18:08:02Z","abstract_excerpt":"Evaluating the quality of machine-generated natural language content is a challenging task in Natural Language Processing (NLP). Recently, large language models (LLMs) like GPT-4 have been employed for this purpose, but they are computationally expensive due to the extensive token usage required by complex evaluation prompts. In this paper, we propose a prompt optimization approach that uses a smaller, fine-tuned language model to compress input data for evaluation prompt, thus reducing token usage and computational cost when using larger LLMs for downstream evaluation. Our method involves a t"},"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":"2412.16120","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T18:08:02Z","cross_cats_sorted":[],"title_canon_sha256":"3111889bf96bf419935b9bd99291daade64438a5afebc9a9ab3b60f10dccb997","abstract_canon_sha256":"d3f5de3ffa37b8b6e67813f3a9062db83683e137c7b25746161bf7cd8dfd274e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:35.392192Z","signature_b64":"WnT10Mne9Wbvom7skKU8pS13xjmlYbIuO2QeKTWjVD9MwT7Bocf7dUu8J/Pxwy5/+K+ZXWBoyPQqAl3FnsBSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"907f727dc1eef9b55b7e8d5c860db1e29e3adcc22f28a0533f21ab5f1ba4a858","last_reissued_at":"2026-07-05T09:52:35.391692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:35.391692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metrics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniil Larionov, Steffen Eger","submitted_at":"2024-12-20T18:08:02Z","abstract_excerpt":"Evaluating the quality of machine-generated natural language content is a challenging task in Natural Language Processing (NLP). Recently, large language models (LLMs) like GPT-4 have been employed for this purpose, but they are computationally expensive due to the extensive token usage required by complex evaluation prompts. In this paper, we propose a prompt optimization approach that uses a smaller, fine-tuned language model to compress input data for evaluation prompt, thus reducing token usage and computational cost when using larger LLMs for downstream evaluation. Our method involves a t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16120","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/2412.16120/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":"2412.16120","created_at":"2026-07-05T09:52:35.391742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16120v1","created_at":"2026-07-05T09:52:35.391742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16120","created_at":"2026-07-05T09:52:35.391742+00:00"},{"alias_kind":"pith_short_12","alias_value":"SB7XE7OB5343","created_at":"2026-07-05T09:52:35.391742+00:00"},{"alias_kind":"pith_short_16","alias_value":"SB7XE7OB5343KW36","created_at":"2026-07-05T09:52:35.391742+00:00"},{"alias_kind":"pith_short_8","alias_value":"SB7XE7OB","created_at":"2026-07-05T09:52:35.391742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SB7XE7OB5343KW36RVOIMDNR4K","json":"https://pith.science/pith/SB7XE7OB5343KW36RVOIMDNR4K.json","graph_json":"https://pith.science/api/pith-number/SB7XE7OB5343KW36RVOIMDNR4K/graph.json","events_json":"https://pith.science/api/pith-number/SB7XE7OB5343KW36RVOIMDNR4K/events.json","paper":"https://pith.science/paper/SB7XE7OB"},"agent_actions":{"view_html":"https://pith.science/pith/SB7XE7OB5343KW36RVOIMDNR4K","download_json":"https://pith.science/pith/SB7XE7OB5343KW36RVOIMDNR4K.json","view_paper":"https://pith.science/paper/SB7XE7OB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16120&json=true","fetch_graph":"https://pith.science/api/pith-number/SB7XE7OB5343KW36RVOIMDNR4K/graph.json","fetch_events":"https://pith.science/api/pith-number/SB7XE7OB5343KW36RVOIMDNR4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SB7XE7OB5343KW36RVOIMDNR4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SB7XE7OB5343KW36RVOIMDNR4K/action/storage_attestation","attest_author":"https://pith.science/pith/SB7XE7OB5343KW36RVOIMDNR4K/action/author_attestation","sign_citation":"https://pith.science/pith/SB7XE7OB5343KW36RVOIMDNR4K/action/citation_signature","submit_replication":"https://pith.science/pith/SB7XE7OB5343KW36RVOIMDNR4K/action/replication_record"}},"created_at":"2026-07-05T09:52:35.391742+00:00","updated_at":"2026-07-05T09:52:35.391742+00:00"}