Skip to content

Lasting Effects of Abstract Pretraining Beyond Perplexity

Sep 2026 · arXiv.org · Vol abs/2609.38764 · 1 citation · 38 references
Computer Science

TL;DR

The results show that early abstract training can reliably shape the capabilities language models later acquire, and in small language models, such a warm-up improves specific capabilities that are not reflected in language-modeling perplexity.

Abstract

Language models are typically pretrained from random initialization. Recent work challenges this convention, showing that a brief warm-up on abstract, algorithmically generated data can provide a better starting point for subsequent learning of natural language. In this paper, we show that in small language models, such a warm-up improves specific capabilities that are not reflected in language-modeling perplexity. Our warm-up uses an abstract stack-manipulation task that requires compositional and state-tracking capabilities. Allocating as little as 1% of pretraining tokens to this data improves multi-hop question answering by up to 3.9 F1 points on MUSIQUE, with additional gains on HOTPOTQA and 2WIKIMULTIHOPQA despite comparable language-modeling perplexity. Controlled experiments show that the warm-up substantially accelerates the acquisition of deeper reasoning chains. We also explore what drives this transfer. First, the structure of the data matters: replacing the stack task with a queue fails to produce the same gains. Second, the gains are specific: performance improves on sequential reasoning chains, with no consistent benefit on tasks that combine or compare independent facts. Third, timing matters: mixing abstract data with natural language is far less effective than an initial dedicated phase, and exposure after pretraining completely removes the benefits. The early advantage persists through billions of subsequent language tokens. These results show that early abstract training can reliably shape the capabilities language models later acquire.

View source

Similar papers

#machine learning Preprint Oct 2026

Conditional Transfer from Controlled Pretraining Mixtures to Code

Synthetic tasks are increasingly used both as probes of language-model capability and as pretraining data. Both uses are often justified by loss reduction: falling loss is treated as informative, and faster loss reduction with more sampling as evidence that a task is worth sampling. We separate three signals. A task is...

Ohad Rubin · 0 citations
Preprint Aug 2026

Rethinking Expressivity and Efficiency in Test-Time Training

Under the standard approximation of taking gradients at the chunk-start weights, a closed-form state transition is derived that exactly reproduces the chunk-end fast-weight and momentum states of the per-token recurrence of Test-Time Training.

Zeyun Zhong, Joya Chen, Manuel Martín et al. · 2 citations
#machine learning Preprint Oct 2026

HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning

Long-form thinking traces can substantially improve the multi-step reasoning performance of large language models (LLMs), but they introduce high inference-time overhead, with latency dominated by sequential decoding. We propose HyperThink, a text-to-parameter approach that amortizes this reasoning computation into a s...

Donggyun Kim, Jack Lu, Chanwoo Kim et al. · 1 citation

UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?

Whether unlearning runs exhibit exploitable structure in weight space is investigated, and it is observed that models from different runs still lie in a shared evaluation-performance basin, suggesting that stronger models may be recovered through an unlearning-tailored soup strategy, reducing the need for repeated tuni...

Pu-Ning Yang, Qi-Zhou Wang, Jun-Chi Yu et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

MIT News · Artificial Intelligence Oct 23, 2026

Q&A: How AI came to model the “messy” human mind

Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.