Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor
Abstract:Narang et al. (2021) evaluated 40+ Transformer modifications at T5-base scale and concluded that most did not transfer. Five years later, the typical working regime has moved to 1-3B parameters, downstream evaluation has replaced pretraining perplexity, and a substantially different catalogue of modifications has emerged. We revisit their question by testing 20 post-2021 Transformer modifications at 1.2B and 3B under strict iso-data, iso-compute, iso-recipe control, with a multi-seed baseline noise floor and CLIMB-12 downstream evaluation as the primary metric. The central finding reproduces theirs at this curated set: most modifications do not transfer. Of the 20 modifications, only two clear Bonferroni correction at 1.2B; one of those two further fails to train stably at 3B under the shared recipe. We also find that the loss-downstream gap reported by Tay et al. (2023) enlarges several-fold for attention-output modifications: two significant failures converge to within 2-3% of baseline validation loss yet drop 6-16 CLIMB-points. We conclude that noise-floor reporting, downstream evaluation, and cross-scale stability testing are now prerequisites for architecture comparisons at 1-3B.
| Comments: | 19 pages, 3 figures, under review at EMNLP 2026 |
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.20798 [cs.LG] |
| (or arXiv:2605.20798v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.20798
arXiv-issued DOI via DataCite (pending registration)
|
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
References & Citations
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
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.
More from arXiv — NLP / Computation & Language
-
Shiny Stories, Hidden Struggles: Investigating the Representation of Disability Through the Lens of LLMs
May 21
-
Leveraging Large Language Models for Sentiment Analysis: Multi-Modal Analysis of Decentraland's MANA Token
May 21
-
Improving Quantized Model Performance in Qualitative Analysis with Multi-Pass Prompt Verification
May 21
-
Parallel LLM Reasoning for Bias-Resilient, Robust Conceptual Abstraction
May 21
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.