{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:01:47Z","timestamp":1750309307349,"version":"3.41.0"},"reference-count":20,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["XRDS"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1145\/3589654","type":"journal-article","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T20:41:25Z","timestamp":1681332085000},"page":"60-62","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["The Inexplicable Efficacy of Language Models"],"prefix":"10.1145","volume":"29","author":[{"given":"Rachith","family":"Aiyappa","sequence":"first","affiliation":[{"name":"Indiana University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zoher","family":"Kachwala","sequence":"additional","affiliation":[{"name":"Indiana University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,12]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944966"},{"key":"e_1_2_1_2_1","volume-title":"et al. Efficient estimation of word representations in vector space. arXiv:1301.3781 [cs]","author":"Mikolov T.","year":"2013","unstructured":"Mikolov, T. et al. Efficient estimation of word representations in vector space. arXiv:1301.3781 [cs]. 2013."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_2_1_4_1","volume-title":"OpenAI. (Feb. 14","author":"Radford A.","year":"2019","unstructured":"Radford, A. et al. Language models are unsupervised multitask learners. OpenAI. (Feb. 14, 2019); https:\/\/openai.com\/research\/better-language-models"},{"key":"e_1_2_1_5_1","volume-title":"et al. DeBERTa: Decoding-enhanced BERT with disentangled attention. arXiv preprint arXiv:2006.03654","author":"He P.","year":"2020","unstructured":"He, P. et al. DeBERTa: Decoding-enhanced BERT with disentangled attention. arXiv preprint arXiv:2006.03654. 2020."},{"key":"e_1_2_1_6_1","first-page":"1901","article-title":"Language models are few-shot learners. In Advances in Neural Information Processing Systems, vol. 33","volume":"1877","author":"Brown T.","year":"2020","unstructured":"Brown, T. et al. Language models are few-shot learners. In Advances in Neural Information Processing Systems, vol. 33. Curran Associates, 2020, 1877--1901.","journal-title":"Curran Associates"},{"key":"e_1_2_1_7_1","volume-title":"et al. Realtoxicityprompts: Evaluating neural toxic degeneration in language models. arXiv preprint arXiv:2009.11462","author":"Gehman S.","year":"2020","unstructured":"Gehman, S. et al. Realtoxicityprompts: Evaluating neural toxic degeneration in language models. arXiv preprint arXiv:2009.11462. 2020."},{"key":"e_1_2_1_8_1","volume-title":"et al. Ethical and social risks of harm from language models. arXiv preprint arXiv:2112.04359","author":"Weidinger L.","year":"2021","unstructured":"Weidinger, L. et al. Ethical and social risks of harm from language models. arXiv preprint arXiv:2112.04359. 2021."},{"key":"e_1_2_1_9_1","volume-title":"the Proceedings of the 30th USENIX Security Symposium (USENIX Security 21)","author":"Carlini N.","year":"2021","unstructured":"Carlini, N. et al. Extracting training data from large language models. In the Proceedings of the 30th USENIX Security Symposium (USENIX Security 21). UNISEX Association, 2021, 2633--2650."},{"key":"e_1_2_1_10_1","volume-title":"et al. Alignment of language agents. arXiv preprint arXiv:2103.14659","author":"Kenton Z.","year":"2021","unstructured":"Kenton, Z. et al. Alignment of language agents. arXiv preprint arXiv:2103.14659, 2021."},{"key":"e_1_2_1_11_1","volume-title":"et al. Understanding the capabilities, limitations, and societal impact of large language models. arXiv preprint arXiv:2102.02503","author":"Tamkin A.","year":"2021","unstructured":"Tamkin, A. et al. Understanding the capabilities, limitations, and societal impact of large language models. arXiv preprint arXiv:2102.02503. 2021."},{"key":"e_1_2_1_12_1","volume-title":"et al. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416","author":"Chung H. W.","year":"2022","unstructured":"Chung, H. W. et al. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416. 2022."},{"key":"e_1_2_1_13_1","volume-title":"et al. Training language models to follow instructions with human feedback. arXiv preprint arXiv:2203.02155","author":"Ouyang L.","year":"2022","unstructured":"Ouyang, L. et al. Training language models to follow instructions with human feedback. arXiv preprint arXiv:2203.02155. 2022."},{"key":"e_1_2_1_14_1","volume-title":"et al. Annotation artifacts in natural language inference data. arXiv preprint arXiv:1803.02324","author":"Gururangan S.","year":"2018","unstructured":"Gururangan, S. et al. Annotation artifacts in natural language inference data. arXiv preprint arXiv:1803.02324. 2018."},{"key":"e_1_2_1_15_1","volume-title":"et al. BERT rediscovers the classical NLP pipeline. arXiv preprint arXiv:1905.05950","author":"Tenney I.","year":"2019","unstructured":"Tenney, I. et al. BERT rediscovers the classical NLP pipeline. arXiv preprint arXiv:1905.05950. 2019."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00349"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1275"},{"key":"e_1_2_1_18_1","volume-title":"et al. Holistic evaluation of language models. arXiv preprint arXiv:2211.09110","author":"Liang P.","year":"2022","unstructured":"Liang, P. et al. Holistic evaluation of language models. arXiv preprint arXiv:2211.09110. 2022."},{"key":"e_1_2_1_19_1","volume-title":"the Proceedings of the 38th International Conference on Machine Learning.","author":"Ramesh A.","year":"2021","unstructured":"Ramesh, A. et al. Zero-shot text-to-image generation. In the Proceedings of the 38th International Conference on Machine Learning. 2021, 8821--8831."},{"key":"e_1_2_1_20_1","volume-title":"Exploring the efficacy of pre-trained checkpoints in text-to-music generation task. arXiv preprint arXiv:2211.11216","author":"Wu S.","year":"2022","unstructured":"Wu, S. and Sun, M. Exploring the efficacy of pre-trained checkpoints in text-to-music generation task. arXiv preprint arXiv:2211.11216. 2022."}],"container-title":["XRDS: Crossroads, The ACM Magazine for Students"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589654","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:46Z","timestamp":1750291426000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":20,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["10.1145\/3589654"],"URL":"https:\/\/doi.org\/10.1145\/3589654","relation":{},"ISSN":["1528-4972","1528-4980"],"issn-type":[{"type":"print","value":"1528-4972"},{"type":"electronic","value":"1528-4980"}],"subject":[],"published":{"date-parts":[[2023,3]]},"assertion":[{"value":"2023-04-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}