ReadingMachine: A Computational Methodology for Structured Corpus Reading and Large-Scale Synthesis
cs.CL
Submitted: 2026-06-05
Updated: 2026-09-25
Comments: 32 pages, 1 figure Fixed two errors in Figure 1 and replaced the figure with an improved rendering of the workflow
License: http://creativecommons.org/licenses/by/4.0/
The gist: ReadingMachine is a computational methodology for structured corpus reading that uses large language models to perform bounded reading operations over entire document collections.
Terminology
Abstract
ReadingMachine is a computational methodology for structured corpus reading that uses large language models to perform bounded reading operations over entire document collections. Rather than relying on retrieval or recursive summarization, the approach decomposes analysis into inspectable stages including insight extraction, semantic clustering, theme generation, and iterative omission detection. By delaying irreversible compression and explicitly tracking intermediate representations, the method prioritizes coverage, traceability, and preservation of disagreement across large corpora. The system is demonstrated on a heterogeneous corpus of 152 industrial policy documents, producing more than 17,500 extracted insights and a structured thematic map. ReadingMachine is released as an open-source experimental framework for large-scale qualitative synthesis and corpus analysis.
Sources
- TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
- ReAct: Synergizing Reasoning and Acting in Language Models
- BERTopic: Neural topic modeling with a class-based TF-IDF procedure
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
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