A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models

[2608.15102] A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2608.15102 (cs) [Submitted on 15 Aug 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models Authors: Amrit Gopinath , Raghul , Durairaj Thenmozhi View a PDF of the paper titled A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models, by Amrit Gopinath and 2 other authors View PDF HTML (experimental) Abstract: We investigate whether Mixture-of-Experts (MoE) language models develop linguistically structured expert routing during bilingual language acquisition. Inspired by the Declarative-Procedural framework, we analyze lexical, grammatical, and syntactic processing in a decoder-only English-German MoE Transformer trained under sequential language exposure. We construct a probe-based validation set and extract token-level routing distributions to quantify category-dependent specialisation using mutual information, routing entropy, and Jensen-Shannon distance. The curriculum-trained model exhibits a peak mutual information of 0.1148 at layer 5, indicating category-dependent differences in routing distributions across linguistic categories. Surprisingly, a no-curriculum baseline trained on mixed English-German data shows stronger aggregate specialisation, reaching a peak mutual information of 0.2599 at the same layer. These results suggest that interpretable linguistic organization emerges within MoE routing patterns even without sequential language exposure. A replication at a second training seed shows that the no-curriculum condition's specialisation concentrates on a single language whose identity is seed-dependent, whereas the curriculum consistently yields a stable, language-balanced routing profile; rather than uniformly increasing specialisation, staged bilingual exposure reduces single-language dominance. The official Github repository: this https URL Comments: 15 pages, 6 figures, 12 tables (including appendix) Subjects: Computation and Language (cs.CL) Cite as: arXiv:2608.15102 [cs.CL] (or arXiv:2608.15102v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.15102 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Amrit Gopinath [ view email ] [v1] Sat, 15 Aug 2026 07:53:12 UTC (430 KB) [v2] Fri, 28 Aug 2026 14:59:30 UTC (430 KB) Full-text links: Access Paper: View a PDF of the paper titled A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models, by Amrit Gopinath and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models#611052
• OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation#924089
• OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation#919860
• THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts#616832
• THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts#616332