{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:22:55Z","timestamp":1763191375485,"version":"3.45.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228901","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Follow Domain-specific Instruction with Verifiable Rewards"],"prefix":"10.1109","author":[{"given":"Shaohan","family":"Huang","sequence":"first","affiliation":[{"name":"Beihang University,Sino-German Joint Software Institute,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University,Sino-German Joint Software Institute,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxing","family":"Qi","sequence":"additional","affiliation":[{"name":"Beihang University,Sino-German Joint Software Institute,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University,Sino-German Joint Software Institute,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongzhi","family":"Luan","sequence":"additional","affiliation":[{"name":"Beihang University,Sino-German Joint Software Institute,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Depei","family":"Qian","sequence":"additional","affiliation":[{"name":"Beihang University,Sino-German Joint Software Institute,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"PaLM: Scaling language modeling with pathways","year":"2022","author":"Chowdhery","key":"ref2"},{"year":"2023","key":"ref3","article-title":"Gpt-4 technical report"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/informatics11030057"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.102963"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5569-1_17"},{"article-title":"Chatlaw: Open-source legal large language model with integrated external knowledge bases","year":"2023","author":"Cui","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626869"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4489826"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.244"},{"article-title":"Finetuned language models are zero-shot learners","volume-title":"ICLR","author":"Wei","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.772"},{"article-title":"Instruction-following evaluation for large language models","year":"2023","author":"Zhou","key":"ref15"},{"key":"ref16","first-page":"27 730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","year":"2023","author":"Zheng","key":"ref17"},{"article-title":"Stanford alpaca: An instruction-following llama model","year":"2023","author":"Taori","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.conll-1.16"},{"article-title":"Self-consistency improves chain of thought reasoning in language models","year":"2022","author":"Wang","key":"ref22"},{"article-title":"Direct preference optimization: Your language model is secretly a reward model","year":"2023","author":"Rafailov","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3412861"},{"article-title":"Pubmed 200k rct: a dataset for sequential sentence classification in medical abstracts","year":"2017","author":"Dernoncourt","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1259"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228901.pdf?arnumber=11228901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:18:51Z","timestamp":1763191131000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228901","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}