Language Models Have Interpretable Narrative Mechanisms

cs.CL

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: 24 pages, 5 figures, 16 tables

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

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

Sources

• DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
• Gemma 2: Improving Open Language Models at a Practical Size
• Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories
• Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders
• Characterizing Narrative Content in Web-scale LLM Pretraining Data
• Narrative Theory-Driven LLM Methods for Automatic Story Generation and Understanding: A Survey
• The Llama 3 Herd of Models
• ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

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