Pith. sign in

REVIEW 1 cited by

DEMix Layers: Disentangling Domains for Modular Language Modeling

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2108.05036 v2 pith:7BGJTZM7 submitted 2021-08-11 cs.CL cs.AI

DEMix Layers: Disentangling Domains for Modular Language Modeling

classification cs.CL cs.AI
keywords domainsdemixexpertsdomainlanguagetrainingaddedconditioning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce a new domain expert mixture (DEMix) layer that enables conditioning a language model (LM) on the domain of the input text. A DEMix layer is a collection of expert feedforward networks, each specialized to a domain, that makes the LM modular: experts can be mixed, added or removed after initial training. Extensive experiments with autoregressive transformer LMs (up to 1.3B parameters) show that DEMix layers reduce test-time perplexity, increase training efficiency, and enable rapid adaptation with little overhead. We show that mixing experts during inference, using a parameter-free weighted ensemble, allows the model to better generalize to heterogeneous or unseen domains. We also show that experts can be added to iteratively incorporate new domains without forgetting older ones, and that experts can be removed to restrict access to unwanted domains, without additional training. Overall, these results demonstrate benefits of explicitly conditioning on textual domains during language modeling.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Capacity and Redundancy Trade-offs in Multi-Task Learning

    cs.LG 2026-07 conditional novelty 4.0

    A shared representation's total per-task information is bounded by capacity plus label redundancy; clustered sharing wins exactly when interference reduction exceeds the redundancy it loses.