{"paper":{"title":"HELO-APR: Enhancing Low-Resource Program Repair through Cross-Lingual Knowledge Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Cross-lingual transfer from C++ raises low-resource language repair Pass@1 from 1.67% to 11.97% on CodeLlama.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Boyang Yang, Liuye Guo, Tao Zheng, Tieke He, Yidong Wan, You Lv, Zhipeng Wang, Zhuowei Wang","submitted_at":"2026-04-18T14:55:11Z","abstract_excerpt":"Large Language Models (LLMs) perform well on automatic program repair (APR) for high-resource programming languages (HRPLs), but their effectiveness drops sharply in low-resource programming languages (LRPLs), due to a lack of sufficient verified buggy-fixed pairs for APR training. To address this challenge, we propose HELO-APR (High-resource Enabled LOw-resource APR), a two-stage APR framework that enables cross-lingual transfer of repair knowledge from HRPLs to LRPLs. HELO-APR (1) constructs high-quality LRPL training data by synthesizing LRPL buggy-fixed pairs from HRPL counterparts, preser"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Using C++ as the source HRPL and Ruby and Rust as the target LRPLs, experiments on xCodeEval show that HELO-APR consistently outperforms strong baselines, increasing Pass@1 from 31.32% to 48.65% on DeepSeek-Coder-6.7B and from 1.67% to 11.97% on CodeLlama-7B, while improving syntactic validity by raising the average target compilation rate on CodeLlama from 49.77% to 91.98%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that synthesizing LRPL buggy-fixed pairs from HRPL counterparts can preserve defect type consistency while ensuring the synthesized code is idiomatic, which is required for the data construction stage to provide effective supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HELO-APR improves LLM-based automatic program repair in low-resource languages by synthesizing cross-lingual training data and using curriculum learning, raising Pass@1 from 31.32% to 48.65% on DeepSeek-Coder for Ruby/Rust targets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Cross-lingual transfer from C++ raises low-resource language repair Pass@1 from 1.67% to 11.97% on CodeLlama.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e3ac8e7e947544067d5a7cc502884fba2e4e99a5117b8cf36df218139dcf4dbc"},"source":{"id":"2604.17016","kind":"arxiv","version":2},"verdict":{"id":"a8aa1d5a-afa0-48cb-bcd1-86abdacf3ced","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T06:29:21.507469Z","strongest_claim":"Using C++ as the source HRPL and Ruby and Rust as the target LRPLs, experiments on xCodeEval show that HELO-APR consistently outperforms strong baselines, increasing Pass@1 from 31.32% to 48.65% on DeepSeek-Coder-6.7B and from 1.67% to 11.97% on CodeLlama-7B, while improving syntactic validity by raising the average target compilation rate on CodeLlama from 49.77% to 91.98%.","one_line_summary":"HELO-APR improves LLM-based automatic program repair in low-resource languages by synthesizing cross-lingual training data and using curriculum learning, raising Pass@1 from 31.32% to 48.65% on DeepSeek-Coder for Ruby/Rust targets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that synthesizing LRPL buggy-fixed pairs from HRPL counterparts can preserve defect type consistency while ensuring the synthesized code is idiomatic, which is required for the data construction stage to provide effective supervision.","pith_extraction_headline":"Cross-lingual transfer from C++ raises low-resource language repair Pass@1 from 1.67% to 11.97% on CodeLlama."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.17016/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"}