Energy-Based Transformers as Predictors of Reading Difficulty

arXiv:2606.23382 · cs.CL, cs.AI · Submitted 2026-06-22 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-06-22

Updated: 2026-09-01

Code: https://github.com/jakdot/energy-transformers-reading-difficulty

Project page: http://skylion007.github.io/OpenWebTextCorpus

Terminology

• Transformer — 55× in this paper · explained in 2 episodes
• Attention Entropy — 28× in this paper · explained in 2 episodes
• Associative Memory — 13× in this paper · explained in 2 episodes
• Transformer Models — 4× in this paper · explained in 2 episodes
• Attention Mechanism — 2× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• NRGPT: An Energy-based Alternative for GPT
• Modern Methods in Associative Memory
• N-gram-like Language Models Predict Reading Time Best
• To model human linguistic prediction, make LLMs less superhuman
• Hopfield Networks is All You Need

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering