Double Trouble: Bilingual Pretraining Leaves Language-Conditioned Effects in Shared-Language Representations
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
arXiv:2608.26576 (cs)
[Submitted on 27 Aug 2026]
Title:Double Trouble: Bilingual Pretraining Leaves Language-Conditioned Effects in Shared-Language Representations
View a PDF of the paper titled Double Trouble: Bilingual Pretraining Leaves Language-Conditioned Effects in Shared-Language Representations, by Anjishnu Mukherjee and 2 other authors
View PDF
HTML (experimental)
Abstract:When researchers compare multilingual models for probing, interpretability, or cross-lingual transfer, they often align embedding spaces and assume that shared-language representations are comparable. We show that this assumption can be premature for decoder-only models. We pretrain paired 310M-parameter models (one English-only, one bilingual) across eight typologically diverse languages, separately controlling for English exposure, total compute, and document overlap. After aligning on shared English vocabulary, we test held-out words and find that token embeddings look similar after alignment, but the deeper hidden states that the model uses for prediction do not. This gap holds for all eight languages and survives controls for document overlap and alternative alignment methods. This hidden-state mismatch grows through middle transformer layers, suggesting that it arises from contextual processing rather than the input representations where alignment is performed. Embedding alignment can mask real differences in how models internally represent a shared language, which matters for any downstream study that treats aligned models as interchangeable.
| Comments: | Published as a conference paper at EMNLP 2026 (Main) |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2608.26576 [cs.CL] |
| (or arXiv:2608.26576v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.26576
arXiv-issued DOI via DataCite (pending registration)
|
Submission history
From: Anjishnu Mukherjee [view email][v1] Thu, 27 Aug 2026 03:39:24 UTC (1,709 KB)
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled Double Trouble: Bilingual Pretraining Leaves Language-Conditioned Effects in Shared-Language Representations, by Anjishnu Mukherjee and 2 other authors
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
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 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
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
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.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.