{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:36:55Z","timestamp":1772933815237,"version":"3.50.1"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11400779","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"6707-6712","source":"Crossref","is-referenced-by-count":0,"title":["Neural Activation Patterns Across Language Model Architectures: A Comprehensive Analysis of Cognitive Task Performance"],"prefix":"10.1109","author":[{"given":"Mahdi Naser","family":"Moghadasi","sequence":"first","affiliation":[{"name":"BrightMind AI,Research Division,Seattle,WA"}]},{"given":"Faezeh","family":"Ghaderi","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington,Arlington,TX"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"issue":"8","key":"ref4","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref5","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Textbooks are all you need","author":"Gunasekar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"BLOOM: A 176B-parameter open-access multilingual language model","author":"Scao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"StableLM: Stability AI Language Models","year":"2023","journal-title":"GitHub repository"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4992"},{"key":"ref11","article-title":"Cognitive psychology","author":"Sternberg","year":"2019","journal-title":"Cengage Learning"},{"key":"ref12","article-title":"Human problem solving","author":"Newell","year":"1972","journal-title":"Prentice-Hall"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.460"},{"key":"ref15","first-page":"8844","article-title":"Measuring mathematical problem solving with the MATH dataset","volume-title":"Proceedings of NeurIPS","author":"Hendrycks"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S18-1001"},{"key":"ref17","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"4459","article-title":"Identifying the human values behind arguments","volume-title":"Proceedings of ACL","author":"Talbot"},{"key":"ref19","article-title":"Towards a human-like open-domain chatbot","author":"Adiwardana","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"LEAP-OF-THOUGHT: Teaching pre-trained models to systematically reason over implicit premises","author":"Talmor","year":"2020","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"WorldTree: A corpus of explanation graphs for elementary science questions supporting multi-hop inference","volume-title":"Proceedings of LREC","author":"Jansen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1269"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.244"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013027"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4828"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1445"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"issue":"241","key":"ref29","first-page":"1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref30","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proceedings of ICML","author":"Frantar"},{"key":"ref31","first-page":"14014","article-title":"Are sixteen heads really better than one?","volume-title":"Proceedings of NeurIPS","author":"Michel"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.259"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref34","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proceedings of NeurIPS","author":"Paszke"},{"key":"ref35","article-title":"Mixed precision training","volume-title":"Proceedings of ICLR","author":"Micikevicius"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1224"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00422"},{"key":"ref38","article-title":"On identifiability in transformers","volume-title":"Proceedings of ICLR","author":"Brunner"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1355"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.279"},{"key":"ref41","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"15318","article-title":"LLM.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proceedings of NeurIPS","author":"Dettmers"},{"key":"ref43","article-title":"Holistic evaluation of language models","author":"Liang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2022","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"issue":"6","key":"ref46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3530811","article-title":"git: A survey","volume":"55","author":"Tay","year":"2022","journal-title":"ACM Computing Surveys"},{"key":"ref47","first-page":"430","article-title":"Pathways: Asynchronous distributed dataflow for ML","volume-title":"Proceedings of MLSys","author":"Narang"},{"key":"ref48","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proceedings of NeurIPS","author":"Lewis"},{"issue":"120","key":"ref49","first-page":"1","article-title":"Switch transformer: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref50","article-title":"CodeGen: An open large language model for code with multi-turn program synthesis","volume-title":"Proceedings of ICLR","author":"Nijkamp"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11400779.pdf?arnumber=11400779","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:52:32Z","timestamp":1772866352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11400779\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11400779","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}