{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:07:42Z","timestamp":1790269662402,"version":"4.1.0"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"National Science Foundation","award":["DGE-2234660"],"award-info":[{"award-number":["DGE-2234660"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tg.2025.3594304","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T18:33:30Z","timestamp":1753986810000},"page":"473-482","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Language Models With the\n                    <i>New York Times Connections<\/i>\n                    Puzzle"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8194-8854","authenticated-orcid":false,"given":"Graham","family":"Todd","sequence":"first","affiliation":[{"name":"New York University Tandon","place":["Brooklyn, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Merino","sequence":"additional","affiliation":[{"name":"New York University Tandon","place":["Brooklyn, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sam","family":"Earle","sequence":"additional","affiliation":[{"name":"New York University Tandon","place":["Brooklyn, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3128-4598","authenticated-orcid":false,"given":"Julian","family":"Togelius","sequence":"additional","affiliation":[{"name":"New York University Tandon","place":["Brooklyn, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"What connects only connect and New York Times? Games similarity puzzles host","author":"Abdul","year":"2023"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1410","article-title":"Sentence-BERT: Sentence embeddings using Siamese BERT-networks","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Reimers","year":"2019"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref5","article-title":"AgentBench: Evaluating LLMs as agents","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-023-01659-w"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CoG60054.2024.10645557"},{"key":"ref11","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref12","article-title":"Can large language models play text games well? Current state-of-the-art and open questions","author":"Tsai","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade9097"},{"key":"ref14","article-title":"The chess transformer: Mastering play using generative language models","author":"Noever","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/AI4I49448.2020.00012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1062"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.26503\/dl.v2016i1.752"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2361"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3582437.3587211"},{"key":"ref21","first-page":"13455","article-title":"ByteSized32: A corpus and challenge task for generating task-specific world models expressed as text games","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Wang","year":"2023"},{"key":"ref22","first-page":"231","article-title":"Word autobots: Using transformers for word association in the game codenames","volume-title":"Proc. AAAI Conf. Artif. Intell. Interactive Digit. Entertainment","author":"Jaramillo","year":"2020"},{"key":"ref23","article-title":"Solving and generating NPR sunday puzzles with large language models","author":"Zhao","year":"2023"},{"key":"ref24","first-page":"11409","article-title":"Decrypting cryptic crosswords: Semantically complex wordplay puzzles as a target for NLP","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rozner","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.219"},{"key":"ref26","article-title":"Can ChatGPT solve NYTs connections?","author":"Perowne","year":"2023"},{"key":"ref27","first-page":"21219","article-title":"Connecting the dots: Evaluating abstract reasoning capabilities of LLMs using the New York Times connections word game","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Samdarshi","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref29","first-page":"1218","article-title":"A robustly optimized BERT pre-training approach with post-training","volume-title":"Proc. 20th Chin. Nat. Conf. Comput. Linguistics","author":"Zhuang","year":"2021"},{"key":"ref30","first-page":"16857","article-title":"MPNet: Masked and permuted pre-training for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2020"},{"key":"ref31","first-page":"5776","article-title":"MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref34","article-title":"OpenAI o1 model details","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v20i1.31869"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-8847-5_10"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7782673\/11693993\/11106261-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/11693993\/11106261.pdf?arnumber=11106261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:44:03Z","timestamp":1790268243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11106261\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":36,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tg.2025.3594304","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}