Source identity
| Field | Recorded value |
|---|---|
| Source type | GitHub source |
| Original record | Janady13/awesome-generative-engine-optimization / papers-and-studies/README.md |
| Date | Not specified in source |
| Repository | Janady13/awesome-generative-engine-optimization |
| Revision | a0b5ebd239ead87fdae46ec5c5862eec82faa239 |
| Branch | main |
| Path or archive member | papers-and-studies/README.md |
| Original SHA-256 | fd48b182833c4afe0c976043b0e49a9673208dacc03535e0bbe865d3e83054b0 |
| Git blob SHA | 1f8bcd8bbbaeb76b49ab897569b11790545269ec |
| Reading-copy SHA-256 | fd48b182833c4afe0c976043b0e49a9673208dacc03535e0bbe865d3e83054b0 |
Recovered source transcript
Download complete source text ↓15 lines · 0.6 KB
# Papers and Studies
This folder collects technical papers, research articles, and analysis relevant to Generative Engine Optimization (GEO), LLM behavior, and AI-powered search.
Topics include:
- Citation bias in LLM outputs
- Training data influence on AI recommendations
- Retrieval vs. non-retrieval model behavior
- Protocols like `llms.txt` and AI crawler control
- Evaluation benchmarks for generative search
Where possible, we link to the original source. For distribution-restricted papers, we include summaries or links only.
Know a paper worth including? Open a PR or issue with the link.