gbanyan
43c025e060
- Add complete experiments directory with pilot study infrastructure - 5 experimental conditions (direct, expert-only, attribute-only, full-pipeline, random-perspective) - Human assessment tool with React frontend and FastAPI backend - AUT flexibility analysis with jump signal detection - Result visualization and metrics computation - Add novelty-driven agent loop module (experiments/novelty_loop/) - NoveltyDrivenTaskAgent with expert perspective perturbation - Three termination strategies: breakthrough, exhaust, coverage - Interactive CLI demo with colored output - Embedding-based novelty scoring - Add DDC knowledge domain classification data (en/zh) - Add CLAUDE.md project documentation - Update research report with experiment findings Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Research: Expert-Augmented LLM Ideation
This folder contains research materials for the academic paper on the novelty-seeking system.
Files
| File | Description |
|---|---|
literature_review.md |
Comprehensive literature review covering semantic distance theory, conceptual blending, design fixation, LLM limitations, and related work |
references.md |
55+ academic references with links to papers |
theoretical_framework.md |
The "Semantic Gravity" theoretical model and testable hypotheses |
paper_outline.md |
Complete paper structure, experimental design, and target venues |
Key Theoretical Contribution
"Semantic Gravity": LLMs exhibit a tendency to generate outputs clustered around high-probability regions of their training distribution, limiting creative novelty. Expert perspectives provide "escape velocity" to break free from this gravity.
Core Hypotheses
- H1: Multi-expert generation → higher semantic diversity
- H2: Multi-expert generation → lower patent overlap (higher novelty)
- H3: Diversity increases with expert count (diminishing returns ~4-6)
- H4: Expert source affects unconventionality of ideas
Target Venues
- CHI (ACM Conference on Human Factors in Computing Systems)
- CSCW (ACM Conference on Computer-Supported Cooperative Work)
- Creativity & Cognition (ACM Conference)
- IJHCS (International Journal of Human-Computer Studies)
Next Steps
- Design concrete experiment protocol
- Add measurement code to existing system
- Collect experimental data
- Conduct human evaluation
- Write and submit paper