{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EU5IZPDHDGWKSFQHHUOFMGFLS2","short_pith_number":"pith:EU5IZPDH","schema_version":"1.0","canonical_sha256":"253a8cbc6719aca916073d1c5618ab968083e07b4ab71cf0c2137f081227ca11","source":{"kind":"arxiv","id":"2307.10928","version":4},"attestation_state":"computed","paper":{"title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Doyoung Kim, Hyeonbin Hwang, James Thorne, Juho Kim, Minjoon Seo, Seonghyeon Ye, Seungone Kim, Sungdong Kim, Yongrae Jo","submitted_at":"2023-07-20T14:56:35Z","abstract_excerpt":"Evaluation of Large Language Models (LLMs) is challenging because instruction-following necessitates alignment with human values and the required set of skills varies depending on the instruction. However, previous studies have mainly focused on coarse-grained evaluation (i.e. overall preference-based evaluation), which limits interpretability since it does not consider the nature of user instructions that require instance-wise skill composition. In this paper, we introduce FLASK (Fine-grained Language Model Evaluation based on Alignment Skill Sets), a fine-grained evaluation protocol for both"},"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":"2307.10928","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-20T14:56:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a48041a2816b5aba68a53291c1db4fe33fdeeb00c836028cb2ed10691189b8e7","abstract_canon_sha256":"e7bd527f331cc840bbc96651e98b0b3d287e0ff9d5defc93dfbaa3ca32e4982a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:28.447373Z","signature_b64":"m/1YbFhwuob7wPU4mrCqdif0dk4Q0Z8YgeCBnZ04uUNXYvoyV+dV0KntfaFE5zOdMYv3dfeMY4yTe9CoKUlZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"253a8cbc6719aca916073d1c5618ab968083e07b4ab71cf0c2137f081227ca11","last_reissued_at":"2026-07-05T08:07:28.446873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:28.446873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Doyoung Kim, Hyeonbin Hwang, James Thorne, Juho Kim, Minjoon Seo, Seonghyeon Ye, Seungone Kim, Sungdong Kim, Yongrae Jo","submitted_at":"2023-07-20T14:56:35Z","abstract_excerpt":"Evaluation of Large Language Models (LLMs) is challenging because instruction-following necessitates alignment with human values and the required set of skills varies depending on the instruction. However, previous studies have mainly focused on coarse-grained evaluation (i.e. overall preference-based evaluation), which limits interpretability since it does not consider the nature of user instructions that require instance-wise skill composition. In this paper, we introduce FLASK (Fine-grained Language Model Evaluation based on Alignment Skill Sets), a fine-grained evaluation protocol for both"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10928","kind":"arxiv","version":4},"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/2307.10928/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":"2307.10928","created_at":"2026-07-05T08:07:28.446935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.10928v4","created_at":"2026-07-05T08:07:28.446935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10928","created_at":"2026-07-05T08:07:28.446935+00:00"},{"alias_kind":"pith_short_12","alias_value":"EU5IZPDHDGWK","created_at":"2026-07-05T08:07:28.446935+00:00"},{"alias_kind":"pith_short_16","alias_value":"EU5IZPDHDGWKSFQH","created_at":"2026-07-05T08:07:28.446935+00:00"},{"alias_kind":"pith_short_8","alias_value":"EU5IZPDH","created_at":"2026-07-05T08:07:28.446935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05391","citing_title":"LLM-as-a-Verifier: A General-Purpose Verification Framework","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18268","citing_title":"Towards Multi-Agent-Simulation-Based Community Note Evaluation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02109","citing_title":"BADGER: Bridging Agentic and Deterministic Evaluation for Generative Enterprise Reasoning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29420","citing_title":"When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13992","citing_title":"\"The Whole Is Greater Than the Sum of Its Parts\": A Compatibility-Aware Multi-Teacher CoT Distillation Framework","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11206","citing_title":"Evalet: Evaluating Large Language Models through Functional Fragmentation","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09566","citing_title":"LETGAMES: An LLM-Powered Gamified Approach to Cognitive Training for Patients with Cognitive Impairment","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08354","citing_title":"Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":279,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23178","citing_title":"Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19457","citing_title":"Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20131","citing_title":"Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives","ref_index":168,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EU5IZPDHDGWKSFQHHUOFMGFLS2","json":"https://pith.science/pith/EU5IZPDHDGWKSFQHHUOFMGFLS2.json","graph_json":"https://pith.science/api/pith-number/EU5IZPDHDGWKSFQHHUOFMGFLS2/graph.json","events_json":"https://pith.science/api/pith-number/EU5IZPDHDGWKSFQHHUOFMGFLS2/events.json","paper":"https://pith.science/paper/EU5IZPDH"},"agent_actions":{"view_html":"https://pith.science/pith/EU5IZPDHDGWKSFQHHUOFMGFLS2","download_json":"https://pith.science/pith/EU5IZPDHDGWKSFQHHUOFMGFLS2.json","view_paper":"https://pith.science/paper/EU5IZPDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.10928&json=true","fetch_graph":"https://pith.science/api/pith-number/EU5IZPDHDGWKSFQHHUOFMGFLS2/graph.json","fetch_events":"https://pith.science/api/pith-number/EU5IZPDHDGWKSFQHHUOFMGFLS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EU5IZPDHDGWKSFQHHUOFMGFLS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EU5IZPDHDGWKSFQHHUOFMGFLS2/action/storage_attestation","attest_author":"https://pith.science/pith/EU5IZPDHDGWKSFQHHUOFMGFLS2/action/author_attestation","sign_citation":"https://pith.science/pith/EU5IZPDHDGWKSFQHHUOFMGFLS2/action/citation_signature","submit_replication":"https://pith.science/pith/EU5IZPDHDGWKSFQHHUOFMGFLS2/action/replication_record"}},"created_at":"2026-07-05T08:07:28.446935+00:00","updated_at":"2026-07-05T08:07:28.446935+00:00"}