{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T14:51:36Z","timestamp":1748875896386,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650937","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Unlocking Chain of Thought in Base Language Models by Heuristic Instruction"],"prefix":"10.1109","author":[{"given":"Ren","family":"Zhuang","sequence":"first","affiliation":[{"name":"Hangzhou Normal University,School of Information Science and Technology,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ben","family":"Wang","sequence":"additional","affiliation":[{"name":"Hangzhou Normal University,School of Information Science and Technology,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuifa","family":"Sun","sequence":"additional","affiliation":[{"name":"Hangzhou Normal University,School of Information Science and Technology,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanlong","family":"Wang","sequence":"additional","affiliation":[{"name":"Communication University of Zhejiang,College of Media Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Ding","sequence":"additional","affiliation":[{"name":"Hangzhou Normal University,School of Information Science and Technology,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Liu","sequence":"additional","affiliation":[{"name":"Hangzhou Normal University,School of Information Science and Technology,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/29.32278"},{"key":"ref2","first-page":"858","article-title":"Large language models in machine translation","volume-title":"Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)","author":"Brants"},{"key":"ref3","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"article-title":"Automatic chain of thought prompting in large language models","year":"2022","author":"Zhang","key":"ref4"},{"article-title":"Self-consistency improves chain of thought reasoning in language models","year":"2022","author":"Wang","key":"ref5"},{"key":"ref6","first-page":"22 199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Advances in neural information processing systems"},{"article-title":"A survey of large language models","year":"2023","author":"Zhao","key":"ref7"},{"article-title":"Emergent abilities of large language models","year":"2022","author":"Wei","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3624724"},{"article-title":"Galactica: A large language model for science","year":"2022","author":"Taylor","key":"ref10"},{"key":"ref11","article-title":"Are emergent abilities of large language models a mirage?","volume":"36","author":"Schaeffer","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.17"},{"article-title":"Prune once for all: Sparse pre-trained language models","year":"2021","author":"Zafrir","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.92"},{"key":"ref17","first-page":"4149","article-title":"Commonsenseqa: A question answering challenge targeting commonsense knowledge","volume-title":"Proceedings of NAACL-HLT","author":"Talmor"},{"key":"ref18","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"article-title":"Finetuned language models are zero-shot learners","volume-title":"International Conference on Learning Representations","author":"Wei","key":"ref19"},{"article-title":"Chain-of-instructions: Compositional instruction tuning on large language models","year":"2024","author":"Hayati","key":"ref20"},{"article-title":"Finetuned language models are zero-shot learners","year":"2021","author":"Wei","key":"ref21"},{"article-title":"Ext5: Towards extreme multi-task scaling for transfer learning","year":"2021","author":"Aribandi","key":"ref22"},{"key":"ref23","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"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.589"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.782"},{"article-title":"Logicot: Logical chain-of-thought instruction-tuning data collection with gpt-4","year":"2023","author":"Liu","key":"ref26"},{"article-title":"Instruction tuning for large language models: A survey","year":"2023","author":"Zhang","key":"ref27"},{"article-title":"Rationale-augmented ensembles in language models","year":"2022","author":"Wang","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1264"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.653"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w16-2301"},{"article-title":"Albert: A lite bert for self-supervised learning of language representations","year":"2019","author":"Lan","key":"ref32"},{"key":"ref33","article-title":"Well-read students learn better: The impact of student initialization on knowledge distillation","volume":"13","author":"Turc","year":"2019"},{"key":"ref34","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Kenton"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-023-10240-4"},{"key":"ref36","article-title":"Symbolic discovery of optimization algorithms","volume":"36","author":"Chen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.508"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1206"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650937.pdf?arnumber=10650937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:15:15Z","timestamp":1725948915000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650937\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650937","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}