Narrative Lookahead in LLMs: Event-Level Decodability, Predictive Advantage, and Steering

arXiv:2610.18121 · cs.CL · Submitted 2026-10-13 · Read on arXiv

cs.CL

Submitted: 2026-10-13

Updated: 2026-10-13

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Steering — 1× in this paper · explained in 2 episodes

Sources

• RAPTOR: Ridge-Adaptive Logistic Probes
• Gemma 4 Technical Report
• Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
• Olmo 3
• Steering Language Models With Activation Engineering
• Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification
• Representation Engineering: A Top-Down Approach to AI Transparency

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