{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HJ5HEY4FFQTP3YCR7YH5ASKZPC","short_pith_number":"pith:HJ5HEY4F","schema_version":"1.0","canonical_sha256":"3a7a7263852c26fde051fe0fd04959789691e1ee524f1721c7f1f4de2b60c9c7","source":{"kind":"arxiv","id":"2412.10424","version":3},"attestation_state":"computed","paper":{"title":"LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alice Oh, Dongkwan Kim, Eunsu Kim, Juyoung Suk, Niklas Muennighoff, Seungone Kim","submitted_at":"2024-12-10T15:00:32Z","abstract_excerpt":"We introduce LLM-as-an-Interviewer, a novel paradigm for evaluating large language models (LLMs). This approach leverages multi-turn interactions where the LLM interviewer actively provides feedback on responses and poses follow-up questions to the evaluated LLM. At the start of the interview, the LLM interviewer dynamically modifies datasets to generate initial questions, mitigating data contamination. We apply the LLM-as-an-Interviewer framework to evaluate six models on the MATH and DepthQA tasks. Our results show that the framework effectively provides insights into LLM performance, includ"},"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":"2412.10424","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T15:00:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b20a7ad9badd77e7b83026e0e53ed5800b1cae078c5cd50d3334dabf30cd6883","abstract_canon_sha256":"d265b445b7804c8b948f20be178b5c9ef3159ff33d297e5e38eb3ba9da344cc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:16.875614Z","signature_b64":"vzHSME/81PhHc4ShTl3YtT3w7rX4OyN8KvqSNXFu/XgoYgoCG8dzcVKTnl7ei6N5qnVr1xse3BHpdPHRXW++Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a7a7263852c26fde051fe0fd04959789691e1ee524f1721c7f1f4de2b60c9c7","last_reissued_at":"2026-07-05T11:13:16.875024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:16.875024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alice Oh, Dongkwan Kim, Eunsu Kim, Juyoung Suk, Niklas Muennighoff, Seungone Kim","submitted_at":"2024-12-10T15:00:32Z","abstract_excerpt":"We introduce LLM-as-an-Interviewer, a novel paradigm for evaluating large language models (LLMs). This approach leverages multi-turn interactions where the LLM interviewer actively provides feedback on responses and poses follow-up questions to the evaluated LLM. At the start of the interview, the LLM interviewer dynamically modifies datasets to generate initial questions, mitigating data contamination. We apply the LLM-as-an-Interviewer framework to evaluate six models on the MATH and DepthQA tasks. Our results show that the framework effectively provides insights into LLM performance, includ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10424","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/2412.10424/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":"2412.10424","created_at":"2026-07-05T11:13:16.875087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10424v3","created_at":"2026-07-05T11:13:16.875087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10424","created_at":"2026-07-05T11:13:16.875087+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJ5HEY4FFQTP","created_at":"2026-07-05T11:13:16.875087+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJ5HEY4FFQTP3YCR","created_at":"2026-07-05T11:13:16.875087+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJ5HEY4F","created_at":"2026-07-05T11:13:16.875087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14057","citing_title":"Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14057","citing_title":"Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04479","citing_title":"How can LLMs Support Policy Researchers? Evaluating an LLM-Assisted Workflow for Large-Scale Unstructured Data","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJ5HEY4FFQTP3YCR7YH5ASKZPC","json":"https://pith.science/pith/HJ5HEY4FFQTP3YCR7YH5ASKZPC.json","graph_json":"https://pith.science/api/pith-number/HJ5HEY4FFQTP3YCR7YH5ASKZPC/graph.json","events_json":"https://pith.science/api/pith-number/HJ5HEY4FFQTP3YCR7YH5ASKZPC/events.json","paper":"https://pith.science/paper/HJ5HEY4F"},"agent_actions":{"view_html":"https://pith.science/pith/HJ5HEY4FFQTP3YCR7YH5ASKZPC","download_json":"https://pith.science/pith/HJ5HEY4FFQTP3YCR7YH5ASKZPC.json","view_paper":"https://pith.science/paper/HJ5HEY4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10424&json=true","fetch_graph":"https://pith.science/api/pith-number/HJ5HEY4FFQTP3YCR7YH5ASKZPC/graph.json","fetch_events":"https://pith.science/api/pith-number/HJ5HEY4FFQTP3YCR7YH5ASKZPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJ5HEY4FFQTP3YCR7YH5ASKZPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJ5HEY4FFQTP3YCR7YH5ASKZPC/action/storage_attestation","attest_author":"https://pith.science/pith/HJ5HEY4FFQTP3YCR7YH5ASKZPC/action/author_attestation","sign_citation":"https://pith.science/pith/HJ5HEY4FFQTP3YCR7YH5ASKZPC/action/citation_signature","submit_replication":"https://pith.science/pith/HJ5HEY4FFQTP3YCR7YH5ASKZPC/action/replication_record"}},"created_at":"2026-07-05T11:13:16.875087+00:00","updated_at":"2026-07-05T11:13:16.875087+00:00"}