IF-GEO: Conflict-Aware Instruction Fusion for Multi-Query Generative Engine Optimization

2026-01-20

AI Summary

This work addresses the challenges of generative engine optimization (GEO) in multi-query scenarios, where conflicting optimization objectives across queries and limited content budgets hinder performance. The authors propose IF-GEO, a novel framework that adopts a “diverge-then-converge” strategy: it first elicits diverse optimization preferences from representative latent queries and then employs a conflict-aware instruction fusion mechanism to produce a unified revision blueprint guiding document editing. A key innovation is the introduction of a risk-aware stability metric to quantify the robustness of cross-query optimization. Experimental results demonstrate that IF-GEO significantly outperforms existing methods on multi-query GEO benchmarks while exhibiting strong stability and generalization across diverse retrieval settings.

Technology Category

• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Natural Language Processing: Prompt Engineering / Prompting

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

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.

Problem

• Generative Engine Optimization
• multi-query optimization
• conflicting revision requirements
• source visibility
• content budget

Innovation

• Instruction Fusion
• Conflict-Aware Optimization
• Generative Engine Optimization
• Multi-Query Retrieval
• Global Revision Blueprint