{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4UG473MD42PRYXRX5YUN2WD7J6","short_pith_number":"pith:4UG473MD","schema_version":"1.0","canonical_sha256":"e50dcfed83e69f1c5e37ee28dd587f4fa44d7abba9a7648819e8dea8097935f3","source":{"kind":"arxiv","id":"2502.11681","version":4},"attestation_state":"computed","paper":{"title":"RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Flora D. Salim, Gholamreza Haffari, Hao Xue, Lizhen Qu, Yuncheng Hua, Zhuang Li","submitted_at":"2025-02-17T11:16:19Z","abstract_excerpt":"Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment. Through an analysis of high-quality ICL demos, we identified style as a key factor influencing LLM alignment capabilities and explicitly restyled ICL exemplars based on this stylistic framework. Additionally, we combined the restyled demos to achieve a balance between the two conflicting as"},"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":"2502.11681","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T11:16:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82752b247256aca8f30d22509b2f31d39597a4ddedbe453378d3cefe36f6c91e","abstract_canon_sha256":"aff7a426762f8a3000be3509490d7c55298f2744383a7be7e0ee09e56c1d6552"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:31.289431Z","signature_b64":"Rr6XlacHkbDVAEUkGX2g0kXkSa1jCYseq1fI3v9Fr6Ne41fMQyx6Q9wRYLHfUu5sqsp2LBD/M8yb9ywL/u7CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e50dcfed83e69f1c5e37ee28dd587f4fa44d7abba9a7648819e8dea8097935f3","last_reissued_at":"2026-07-05T10:24:31.288932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:31.288932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Flora D. Salim, Gholamreza Haffari, Hao Xue, Lizhen Qu, Yuncheng Hua, Zhuang Li","submitted_at":"2025-02-17T11:16:19Z","abstract_excerpt":"Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost, tuning-free method using in-context learning (ICL) to enhance LLM alignment. Through an analysis of high-quality ICL demos, we identified style as a key factor influencing LLM alignment capabilities and explicitly restyled ICL exemplars based on this stylistic framework. Additionally, we combined the restyled demos to achieve a balance between the two conflicting as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11681","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/2502.11681/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":"2502.11681","created_at":"2026-07-05T10:24:31.288990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11681v4","created_at":"2026-07-05T10:24:31.288990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11681","created_at":"2026-07-05T10:24:31.288990+00:00"},{"alias_kind":"pith_short_12","alias_value":"4UG473MD42PR","created_at":"2026-07-05T10:24:31.288990+00:00"},{"alias_kind":"pith_short_16","alias_value":"4UG473MD42PRYXRX","created_at":"2026-07-05T10:24:31.288990+00:00"},{"alias_kind":"pith_short_8","alias_value":"4UG473MD","created_at":"2026-07-05T10:24:31.288990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20500","citing_title":"Beyond Keywords: Evaluating Large Language Model Classification of Nuanced Ableism","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4UG473MD42PRYXRX5YUN2WD7J6","json":"https://pith.science/pith/4UG473MD42PRYXRX5YUN2WD7J6.json","graph_json":"https://pith.science/api/pith-number/4UG473MD42PRYXRX5YUN2WD7J6/graph.json","events_json":"https://pith.science/api/pith-number/4UG473MD42PRYXRX5YUN2WD7J6/events.json","paper":"https://pith.science/paper/4UG473MD"},"agent_actions":{"view_html":"https://pith.science/pith/4UG473MD42PRYXRX5YUN2WD7J6","download_json":"https://pith.science/pith/4UG473MD42PRYXRX5YUN2WD7J6.json","view_paper":"https://pith.science/paper/4UG473MD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11681&json=true","fetch_graph":"https://pith.science/api/pith-number/4UG473MD42PRYXRX5YUN2WD7J6/graph.json","fetch_events":"https://pith.science/api/pith-number/4UG473MD42PRYXRX5YUN2WD7J6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4UG473MD42PRYXRX5YUN2WD7J6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4UG473MD42PRYXRX5YUN2WD7J6/action/storage_attestation","attest_author":"https://pith.science/pith/4UG473MD42PRYXRX5YUN2WD7J6/action/author_attestation","sign_citation":"https://pith.science/pith/4UG473MD42PRYXRX5YUN2WD7J6/action/citation_signature","submit_replication":"https://pith.science/pith/4UG473MD42PRYXRX5YUN2WD7J6/action/replication_record"}},"created_at":"2026-07-05T10:24:31.288990+00:00","updated_at":"2026-07-05T10:24:31.288990+00:00"}