{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RH2RGGQ4T2E3P4KRLQ5PZ5LTAC","short_pith_number":"pith:RH2RGGQ4","schema_version":"1.0","canonical_sha256":"89f5131a1c9e89b7f1515c3afcf573009fe6e963e20b66b82dcc534a1401fd0d","source":{"kind":"arxiv","id":"2411.09073","version":3},"attestation_state":"computed","paper":{"title":"CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Majumdar, Amulya Yadav, Wenbo Zhang","submitted_at":"2024-11-13T22:56:00Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across various NLP tasks but struggle with code-mixed (or code-switched) language understanding. For example, prior work benchmarking the performance of multilingual LLMs on code-mixed translation tasks has demonstrated that current state-of-the-art multilingual LLMs are ineffective in dealing with code-mixed languages. However, the question of how to improve the capability of multilingual LLMs to handle code-mixed language has not received any attention to date. In this paper, we tackle this research gap by proposing CHAI,"},"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":"2411.09073","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T22:56:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9c79b7df97a0b579dd91011038c7fd2cbae8251112f22d522092ba58f03d6c51","abstract_canon_sha256":"925a58262afd76bab7ea560a62c70b143b94d7d5fad31b8ef79a2eafcf404f0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:01.899686Z","signature_b64":"SHoVj1a/Q53WpL0CbOD8BpM/fZQk0pB0C3nRm3jt/4qhLGRrb3Icn71Xuxrcl48PHqoNF2EJvub63VSBCgCNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89f5131a1c9e89b7f1515c3afcf573009fe6e963e20b66b82dcc534a1401fd0d","last_reissued_at":"2026-07-05T11:34:01.899187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:01.899187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Majumdar, Amulya Yadav, Wenbo Zhang","submitted_at":"2024-11-13T22:56:00Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across various NLP tasks but struggle with code-mixed (or code-switched) language understanding. For example, prior work benchmarking the performance of multilingual LLMs on code-mixed translation tasks has demonstrated that current state-of-the-art multilingual LLMs are ineffective in dealing with code-mixed languages. However, the question of how to improve the capability of multilingual LLMs to handle code-mixed language has not received any attention to date. In this paper, we tackle this research gap by proposing CHAI,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09073","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/2411.09073/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":"2411.09073","created_at":"2026-07-05T11:34:01.899249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09073v3","created_at":"2026-07-05T11:34:01.899249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09073","created_at":"2026-07-05T11:34:01.899249+00:00"},{"alias_kind":"pith_short_12","alias_value":"RH2RGGQ4T2E3","created_at":"2026-07-05T11:34:01.899249+00:00"},{"alias_kind":"pith_short_16","alias_value":"RH2RGGQ4T2E3P4KR","created_at":"2026-07-05T11:34:01.899249+00:00"},{"alias_kind":"pith_short_8","alias_value":"RH2RGGQ4","created_at":"2026-07-05T11:34:01.899249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.14226","citing_title":"Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC","json":"https://pith.science/pith/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC.json","graph_json":"https://pith.science/api/pith-number/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC/graph.json","events_json":"https://pith.science/api/pith-number/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC/events.json","paper":"https://pith.science/paper/RH2RGGQ4"},"agent_actions":{"view_html":"https://pith.science/pith/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC","download_json":"https://pith.science/pith/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC.json","view_paper":"https://pith.science/paper/RH2RGGQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09073&json=true","fetch_graph":"https://pith.science/api/pith-number/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC/graph.json","fetch_events":"https://pith.science/api/pith-number/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC/action/storage_attestation","attest_author":"https://pith.science/pith/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC/action/author_attestation","sign_citation":"https://pith.science/pith/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC/action/citation_signature","submit_replication":"https://pith.science/pith/RH2RGGQ4T2E3P4KRLQ5PZ5LTAC/action/replication_record"}},"created_at":"2026-07-05T11:34:01.899249+00:00","updated_at":"2026-07-05T11:34:01.899249+00:00"}