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

ACL ARR 2026 January Submission7605 Authors

Keywords: Generative Engine Optimization, Large Language Models, Information Retrieval.

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 \emph{``diverge-then-converge''} framework comprising two phases: (i) mining distinct optimization preferences from representative latent queries; (ii) synthesizing a \emph{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.

Paper Type: Long

Research Area: Retrieval-Augmented Language Models

Research Area Keywords: retrieval-augmented generation, text-to-text generation, automatic evaluation, robustness

Languages Studied: English

Submission Number: 7605