Publication
AbbIE: Autoregressive Block-Based Iterative Encoder for Efficient Sequence Modeling
AbbIE is an autoregressive block-based iterative encoder that recursively refines representations, improving perplexity at a fixed parameter budget.
Abstract:
We introduce the Autoregressive Block-Based Iterative Encoder (AbbIE), a novel recursive generalization of the encoder-only Transformer architecture, which achieves better perplexity than a standard Transformer and allows for the dynamic scaling of compute resources at test time. This simple, recursive approach is a complement to scaling large language model (LLM) performance through parameter and token counts. AbbIE performs its iterations in latent space, but unlike latent reasoning models, does not require a specialized dataset or training protocol. We show that AbbIE upward generalizes (ability to generalize to arbitrary iteration lengths) at test time by only using 2 iterations during train time, far outperforming alternative iterative methods. AbbIE’s ability to scale its computational expenditure based on the complexity of the task gives it an up to 12% improvement in zero-shot in-context learning tasks versus other iterative and standard methods and up to 5% improvement in language perplexity. The results from this study open a new avenue to Transformer performance scaling. We perform all of our evaluations on model sizes up to 350M parameters.
Recommended citation: Preslav Aleksandrov, Meghdad Kurmanji, Fernando Garcia Redondo, David O’Shea, William Shen, Alex Iacob, Lorenzo Sani, Xinchi Qiu, Nicola Cancedda, & Nicholas D. Lane. (2025). AbbIE: Autoregressive Block-Based Iterative Encoder for Efficient Sequence Modeling.