IF-GEO: Conflict-Aware Instruction Fusion for Multi-Query Generative Engine Optimization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908776374730752 |
|---|---|
| author | Zhou, Heyang Chen, JiaJia Chen, Xiaolu Bao, Jie Chen, Zhen Liao, Yong |
| author_facet | Zhou, Heyang Chen, JiaJia Chen, Xiaolu Bao, Jie Chen, Zhen Liao, Yong |
| contents | As Generative Engines revolutionize information retrieval by synthesizing direct answers from retrieved sources, ensuring source visibility becomes a significant challenge. Improving it through targeted content revisions is a practical strategy termed Generative Engine Optimization (GEO). However, optimizing a document for diverse queries presents a constrained optimization challenge where heterogeneous queries often impose conflicting and competing revision requirements under a limited content budget. To address this challenge, we propose IF-GEO, a "diverge-then-converge" framework comprising two phases: (i) mining distinct optimization preferences from representative latent queries; (ii) synthesizing a Global Revision Blueprint for guided editing by coordinating preferences via conflict-aware instruction fusion. To explicitly quantify IF-GEO's objective of cross-query stability, we introduce risk-aware stability metrics. Experiments on multi-query benchmarks demonstrate that IF-GEO achieves substantial performance gains while maintaining robustness across diverse retrieval scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_13938 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IF-GEO: Conflict-Aware Instruction Fusion for Multi-Query Generative Engine Optimization Zhou, Heyang Chen, JiaJia Chen, Xiaolu Bao, Jie Chen, Zhen Liao, Yong Information Retrieval Artificial Intelligence As Generative Engines revolutionize information retrieval by synthesizing direct answers from retrieved sources, ensuring source visibility becomes a significant challenge. Improving it through targeted content revisions is a practical strategy termed Generative Engine Optimization (GEO). However, optimizing a document for diverse queries presents a constrained optimization challenge where heterogeneous queries often impose conflicting and competing revision requirements under a limited content budget. To address this challenge, we propose IF-GEO, a "diverge-then-converge" framework comprising two phases: (i) mining distinct optimization preferences from representative latent queries; (ii) synthesizing a Global Revision Blueprint for guided editing by coordinating preferences via conflict-aware instruction fusion. To explicitly quantify IF-GEO's objective of cross-query stability, we introduce risk-aware stability metrics. Experiments on multi-query benchmarks demonstrate that IF-GEO achieves substantial performance gains while maintaining robustness across diverse retrieval scenarios. |
| title | IF-GEO: Conflict-Aware Instruction Fusion for Multi-Query Generative Engine Optimization |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2601.13938 |