2026-09-20T18:49:30Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:25768 2026-09-05T19:24:25Z ddc:004 open_access

Theory of Neural Language Models (Dagstuhl Seminar 25282) Barcelo, Pablo Chiang, David Cybenko, George Strobl, Lena Yang, Andy Dagstuhl Seminar Neural Networks Language Models Automata Logic Model Theory Circuit Complexity This report documents the program and the outcomes of Dagstuhl Seminar 25282 "Theory of Neural Language Models". The seminar aimed to bring researchers together to lay a foundation for continued work on the theory of neural language models, focusing on questions including: How do transformers, RNNs, other NLMs, and their variants, compare with one another in expressivity and trainability? How do the successes and failures of NLMs predicted by theoretical models manifest in practice? What modifications, or what wholly new architectures, are suggested by the theory? Schloss Dagstuhl – Leibniz-Zentrum für Informatik Pablo Barcelo and David Chiang and George Cybenko and Lena Strobl and Andy Yang 2026 Is Part Of Dagstuhl Reports, Volume 15, Issue 7 (2026) Article Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/DagRep.15.7.22 urn:nbn:de:0030-drops-257689 https://drops.dagstuhl.de/entities/document/10.4230/DagRep.15.7.22 eng https://creativecommons.org/licenses/by/4.0/legalcode