{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7P4MQPRZW4UKJLBA7LRVLSCG4K","short_pith_number":"pith:7P4MQPRZ","schema_version":"1.0","canonical_sha256":"fbf8c83e39b728a4ac20fae355c846e29e8ed32c83c65cb5d31723f179ba16fb","source":{"kind":"arxiv","id":"2605.11632","version":2},"attestation_state":"computed","paper":{"title":"Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A preference alignment method called Macro improves the validity of multilingual self-generated counterfactual explanations by 12.55 percent on average while maintaining minimality.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bohao Chu, Jing Yang, Qianli Wang, Simon Ostermann, Yihong Liu, Yilong Wang","submitted_at":"2026-05-12T06:56:18Z","abstract_excerpt":"Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior. Yet extending them beyond English remains challenging: existing methods struggle to produce valid SCEs in non-dominant languages, and a persistent trade-off between validity and minimality undermines explanation quality. We introduce Macro, a preference alignment framework that applies Direct Preference Optimization (DPO) to multilingual SCE g"},"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":"2605.11632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-12T06:56:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a6e1694b654f559b8075b950f5cc4ba25911443e16acdafd56ee72a1e31a47f8","abstract_canon_sha256":"6061ab8a4eb421fa0d89540d86fceb1b7b7ce62edd3a578dd6d1709618ca0067"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:40.563637Z","signature_b64":"sGBm3m+7ydb/XIqid27Rf38CRMAdRL1GMhK/xdmiKPwA2v8ywHiNwaWLncrZlGU1ormVZc20qB1Y6wnOyEMgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbf8c83e39b728a4ac20fae355c846e29e8ed32c83c65cb5d31723f179ba16fb","last_reissued_at":"2026-06-05T01:14:40.562797Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:40.562797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A preference alignment method called Macro improves the validity of multilingual self-generated counterfactual explanations by 12.55 percent on average while maintaining minimality.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bohao Chu, Jing Yang, Qianli Wang, Simon Ostermann, Yihong Liu, Yilong Wang","submitted_at":"2026-05-12T06:56:18Z","abstract_excerpt":"Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior. Yet extending them beyond English remains challenging: existing methods struggle to produce valid SCEs in non-dominant languages, and a persistent trade-off between validity and minimality undermines explanation quality. We introduce Macro, a preference alignment framework that applies Direct Preference Optimization (DPO) to multilingual SCE g"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments across four LLMs and seven typologically diverse languages show that Macro improves validity by 12.55% on average over the chain-of-thought baseline without degrading minimality, while avoiding the severe minimality violations of the translation-based baseline.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The composite scoring function used to construct preference pairs accurately and unbiasedly captures the validity-minimality trade-off across typologically diverse languages and different LLMs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Macro uses Direct Preference Optimization on composite-scored preference pairs to improve validity of multilingual self-generated counterfactual explanations by 12.55% on average without degrading minimality.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A preference alignment method called Macro improves the validity of multilingual self-generated counterfactual explanations by 12.55 percent on average while maintaining minimality.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"28e00cdb8af15cb3ccd9b8b0554f11a65c4b9b02c3c90dd8579829e53e2b0b6e"},"source":{"id":"2605.11632","kind":"arxiv","version":2},"verdict":{"id":"907fb810-b009-4583-a604-482d01beb33c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T01:13:58.101109Z","strongest_claim":"Experiments across four LLMs and seven typologically diverse languages show that Macro improves validity by 12.55% on average over the chain-of-thought baseline without degrading minimality, while avoiding the severe minimality violations of the translation-based baseline.","one_line_summary":"Macro uses Direct Preference Optimization on composite-scored preference pairs to improve validity of multilingual self-generated counterfactual explanations by 12.55% on average without degrading minimality.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The composite scoring function used to construct preference pairs accurately and unbiasedly captures the validity-minimality trade-off across typologically diverse languages and different LLMs.","pith_extraction_headline":"A preference alignment method called Macro improves the validity of multilingual self-generated counterfactual explanations by 12.55 percent on average while maintaining minimality."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11632/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-21T00:31:32.115026Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T14:16:48.159725Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-20T04:02:00.401849Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T11:40:41.514511Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c56bffa2b253209226b768852087a08432da90077ba9ddd798026b1ffe2beb6d"},"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":"2605.11632","created_at":"2026-06-05T01:14:40.562876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11632v2","created_at":"2026-06-05T01:14:40.562876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11632","created_at":"2026-06-05T01:14:40.562876+00:00"},{"alias_kind":"pith_short_12","alias_value":"7P4MQPRZW4UK","created_at":"2026-06-05T01:14:40.562876+00:00"},{"alias_kind":"pith_short_16","alias_value":"7P4MQPRZW4UKJLBA","created_at":"2026-06-05T01:14:40.562876+00:00"},{"alias_kind":"pith_short_8","alias_value":"7P4MQPRZ","created_at":"2026-06-05T01:14:40.562876+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/7P4MQPRZW4UKJLBA7LRVLSCG4K","json":"https://pith.science/pith/7P4MQPRZW4UKJLBA7LRVLSCG4K.json","graph_json":"https://pith.science/api/pith-number/7P4MQPRZW4UKJLBA7LRVLSCG4K/graph.json","events_json":"https://pith.science/api/pith-number/7P4MQPRZW4UKJLBA7LRVLSCG4K/events.json","paper":"https://pith.science/paper/7P4MQPRZ"},"agent_actions":{"view_html":"https://pith.science/pith/7P4MQPRZW4UKJLBA7LRVLSCG4K","download_json":"https://pith.science/pith/7P4MQPRZW4UKJLBA7LRVLSCG4K.json","view_paper":"https://pith.science/paper/7P4MQPRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11632&json=true","fetch_graph":"https://pith.science/api/pith-number/7P4MQPRZW4UKJLBA7LRVLSCG4K/graph.json","fetch_events":"https://pith.science/api/pith-number/7P4MQPRZW4UKJLBA7LRVLSCG4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7P4MQPRZW4UKJLBA7LRVLSCG4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7P4MQPRZW4UKJLBA7LRVLSCG4K/action/storage_attestation","attest_author":"https://pith.science/pith/7P4MQPRZW4UKJLBA7LRVLSCG4K/action/author_attestation","sign_citation":"https://pith.science/pith/7P4MQPRZW4UKJLBA7LRVLSCG4K/action/citation_signature","submit_replication":"https://pith.science/pith/7P4MQPRZW4UKJLBA7LRVLSCG4K/action/replication_record"}},"created_at":"2026-06-05T01:14:40.562876+00:00","updated_at":"2026-06-05T01:14:40.562876+00:00"}