Dai and colleagues: Transformer-XL segment recurrence

What changed

Reused hidden states across text segments with relative positional encoding to extend language-model context beyond a fixed segment.

Scientific scope

Reused hidden states across text segments with relative positional encoding to extend language-model context beyond a fixed segment. Cached-state recurrence does not create unlimited effective memory or backpropagation across all past tokens. Speed and dependency measurements are task-specific.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Cached-state recurrence does not create unlimited effective memory or backpropagation across all past tokens. Speed and dependency measurements are task-specific.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction