Search papers, labs, and topics across Lattice.
The paper introduces FeatGEO, a feature-level multi-objective optimization framework for improving citation visibility in generative answer engines. FeatGEO optimizes interpretable structural, content, and linguistic features of webpages, using a language model to translate these features into natural language, thus decoupling optimization from text generation. Experiments on GEO-Bench show that FeatGEO outperforms token-level baselines in improving citation visibility while maintaining content quality, and that document-level content properties have a stronger influence on citation behavior than lexical edits.
Forget tweaking individual words: optimizing high-level content features is the key to making your work more visible to generative AI citation engines.
Generative answer engines expose content through selective citation rather than ranked retrieval, fundamentally altering how visibility is determined. This shift calls for new optimization methods beyond traditional search engine optimization. Existing generative engine optimization (GEO) approaches primarily rely on token-level text rewriting, offering limited interpretability and weak control over the trade-off between citation visibility and content quality. We propose FeatGEO, a feature-level, multi-objective optimization framework that abstracts webpages into interpretable structural, content, and linguistic properties. Instead of directly editing text, FeatGEO optimizes over this feature space and uses a language model to realize feature configurations into natural language, decoupling high-level optimization from surface-level generation. Experiments on GEO-Bench across three generative engines demonstrate that FeatGEO consistently improves citation visibility while maintaining or improving content quality, substantially outperforming token-level baselines. Further analyses show that citation behavior is more strongly influenced by document-level content properties than by isolated lexical edits, and that the learned feature configurations generalize across language models of different scales.