{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LLJAPIKYQ6KXEXH6SZORPI45DG","short_pith_number":"pith:LLJAPIKY","schema_version":"1.0","canonical_sha256":"5ad207a1588795725cfe965d17a39d1986009f5b93bb140f19ba0ecfc27dd878","source":{"kind":"arxiv","id":"2405.00722","version":2},"attestation_state":"computed","paper":{"title":"LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christin Seifert, J\\\"org Schl\\\"otterer, Paul Youssef, Van Bach Nguyen","submitted_at":"2024-04-26T11:57:21Z","abstract_excerpt":"As NLP models become more complex, understanding their decisions becomes more crucial. Counterfactuals (CFs), where minimal changes to inputs flip a model's prediction, offer a way to explain these models. While Large Language Models (LLMs) have shown remarkable performance in NLP tasks, their efficacy in generating high-quality CFs remains uncertain. This work fills this gap by investigating how well LLMs generate CFs for two NLU tasks. We conduct a comprehensive comparison of several common LLMs, and evaluate their CFs, assessing both intrinsic metrics, and the impact of these CFs on data au"},"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":"2405.00722","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T11:57:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67d6e3407d707ac723c4093d341b13fc16026d515544d205728fe330fbd075b2","abstract_canon_sha256":"42bcbd5f50bc9ab4cc5e9881f132687c24ce9a7183f0f6c4c8b67d78045bb3a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:13.443332Z","signature_b64":"oVdj1sIVlDfTzNWCTUY66soXahrhoTEG9KqU3gs/ipS4QIfgRhDnvXI9vUa+SOv3LFyWEHVzRMSA4gptpUN5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ad207a1588795725cfe965d17a39d1986009f5b93bb140f19ba0ecfc27dd878","last_reissued_at":"2026-07-05T09:34:13.442895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:13.442895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christin Seifert, J\\\"org Schl\\\"otterer, Paul Youssef, Van Bach Nguyen","submitted_at":"2024-04-26T11:57:21Z","abstract_excerpt":"As NLP models become more complex, understanding their decisions becomes more crucial. Counterfactuals (CFs), where minimal changes to inputs flip a model's prediction, offer a way to explain these models. While Large Language Models (LLMs) have shown remarkable performance in NLP tasks, their efficacy in generating high-quality CFs remains uncertain. This work fills this gap by investigating how well LLMs generate CFs for two NLU tasks. We conduct a comprehensive comparison of several common LLMs, and evaluate their CFs, assessing both intrinsic metrics, and the impact of these CFs on data au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00722","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/2405.00722/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":"2405.00722","created_at":"2026-07-05T09:34:13.442951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00722v2","created_at":"2026-07-05T09:34:13.442951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00722","created_at":"2026-07-05T09:34:13.442951+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLJAPIKYQ6KX","created_at":"2026-07-05T09:34:13.442951+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLJAPIKYQ6KXEXH6","created_at":"2026-07-05T09:34:13.442951+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLJAPIKY","created_at":"2026-07-05T09:34:13.442951+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10777","citing_title":"The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLJAPIKYQ6KXEXH6SZORPI45DG","json":"https://pith.science/pith/LLJAPIKYQ6KXEXH6SZORPI45DG.json","graph_json":"https://pith.science/api/pith-number/LLJAPIKYQ6KXEXH6SZORPI45DG/graph.json","events_json":"https://pith.science/api/pith-number/LLJAPIKYQ6KXEXH6SZORPI45DG/events.json","paper":"https://pith.science/paper/LLJAPIKY"},"agent_actions":{"view_html":"https://pith.science/pith/LLJAPIKYQ6KXEXH6SZORPI45DG","download_json":"https://pith.science/pith/LLJAPIKYQ6KXEXH6SZORPI45DG.json","view_paper":"https://pith.science/paper/LLJAPIKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00722&json=true","fetch_graph":"https://pith.science/api/pith-number/LLJAPIKYQ6KXEXH6SZORPI45DG/graph.json","fetch_events":"https://pith.science/api/pith-number/LLJAPIKYQ6KXEXH6SZORPI45DG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLJAPIKYQ6KXEXH6SZORPI45DG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLJAPIKYQ6KXEXH6SZORPI45DG/action/storage_attestation","attest_author":"https://pith.science/pith/LLJAPIKYQ6KXEXH6SZORPI45DG/action/author_attestation","sign_citation":"https://pith.science/pith/LLJAPIKYQ6KXEXH6SZORPI45DG/action/citation_signature","submit_replication":"https://pith.science/pith/LLJAPIKYQ6KXEXH6SZORPI45DG/action/replication_record"}},"created_at":"2026-07-05T09:34:13.442951+00:00","updated_at":"2026-07-05T09:34:13.442951+00:00"}