{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:20:15Z","timestamp":1780726815209,"version":"3.54.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tg.2025.3529117","type":"journal-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T15:16:20Z","timestamp":1736867780000},"page":"665-675","source":"Crossref","is-referenced-by-count":4,"title":["BenchING: A Benchmark for Evaluating Large Language Models in Following Structured Output Format Instruction in Text-Based Narrative Game Tasks"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6824-2634","authenticated-orcid":false,"given":"Pittawat","family":"Taveekitworachai","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1967-8607","authenticated-orcid":false,"given":"Mury F.","family":"Dewantoro","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0863-6276","authenticated-orcid":false,"given":"Yi","family":"Xia","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9803-5408","authenticated-orcid":false,"given":"Pratch","family":"Suntichaikul","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Engineering, Ritsumeikan University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9001-5828","authenticated-orcid":false,"given":"Ruck","family":"Thawonmas","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A Survey of large language models","author":"Zhao","year":"2023"},{"key":"ref2","article-title":"Capabilities of Gemini Models in Medicine","author":"Saab","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cog60054.2024.10645548"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3582437.3587211"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3582437.3587188"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47658-7_26"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47658-7_16"},{"key":"ref8","article-title":"A survey on large language model-based game agents","author":"Hu","year":"2024"},{"key":"ref9","first-page":"1","article-title":"Augmented language models: A survey","author":"Mialon","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref10","article-title":"TALM: Tool augmented language models","author":"Parisi","year":"2022"},{"key":"ref11","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-short.2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-short.2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CoG57401.2023.10333206"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3628454.3629551"},{"key":"ref16","article-title":"Neural story planning","author":"Ye","year":"2023","journal-title":"arXiv:2212.08718"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"3378","DOI":"10.18653\/v1\/2023.acl-long.190","article-title":"DOC: Improving long story coherence with detailed outline control","volume-title":"Proc. the 61st Annu. Meeting Assoc. Comput. Linguistics (Volume 1: Long Papers)","author":"Yang","year":"2023"},{"key":"ref18","first-page":"17659","article-title":"Are large language models capable of generating human-level narratives?","volume-title":"Proc. 2024 Conf. Empirical Methods Natural Lang. Process.","author":"Tian","year":"2024"},{"key":"ref19","article-title":"WHAT-IF: Exploring branching narratives by meta-prompting large language models","author":"Huang","year":"2024","journal-title":"arxiv:2412.10582"},{"key":"ref20","article-title":"SOAP version 1.2","volume":"24","author":"Gudgin","year":"2003","journal-title":"W3C Recommend."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3558912"},{"key":"ref22","first-page":"1","article-title":"Finetuned language models are zero-shot learners","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wei","year":"2022"},{"key":"ref23","first-page":"24824","article-title":"Chain of thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei","year":"2022"},{"key":"ref24","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kojima","year":"2022"},{"key":"ref25","article-title":"A systematic survey of prompt engineering in large language models: Techniques and applications","author":"Sahoo","year":"2024"},{"key":"ref26","article-title":"Introducing ChatGPT","year":"2022"},{"key":"ref27","article-title":"GPT-4 Technical Report","year":"2023","journal-title":"arXiv:2303.08774"},{"key":"ref28","article-title":"PaLM 2 technical report","year":"2023"},{"key":"ref29","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref30","article-title":"Introducing MPT-7B: A new standard for open-source, commercially usable LLMs","author":"Team","year":"2023"},{"key":"ref31","article-title":"The Falcon series of open language models","author":"Almazrouei","year":"2023"},{"key":"ref32","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref33","article-title":"The Llama 3 Herd of Models","author":"Dubey","year":"2024"},{"key":"ref34","article-title":"Emergent abilities of large language models","volume-title":"Trans. Mach. Learn. Res.","author":"Wei","year":"2022"},{"key":"ref35","first-page":"1","article-title":"The RefinedWeb dataset for Falcon LLM: Outperforming curated corpora with web data only","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Penedo","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.620"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3262138"},{"key":"ref38","first-page":"1","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref39","article-title":"Qwen Technical Report","author":"Bai","year":"2023","journal-title":"arXiv:2309.16609"},{"key":"ref40","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29908"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3628454.3628456"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"15607","DOI":"10.18653\/v1\/2023.acl-long.870","article-title":"Can large language models be an alternative to human evaluations?","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics (Volume 1: Long Papers)","author":"Chiang","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.248"},{"key":"ref45","article-title":"Constitutional AI: Harmlessness from AI feedback","author":"Bai","year":"2022","journal-title":"arXiv:2212.08073"},{"key":"ref46","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-00985-0"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/11165227\/10840256.pdf?arnumber=10840256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T05:06:55Z","timestamp":1758085615000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10840256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":47,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tg.2025.3529117","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}