Think Before Writing: Feature-Level Multi-Objective Optimization for Generative Citation Visibility

• URL: http://arxiv.org/abs/2604.19113v1
• Date: Tue, 21 Apr 2026 05:47:04 GMT
• Title: Think Before Writing: Feature-Level Multi-Objective Optimization for Generative Citation Visibility
• Abstract summary: Generative answer engines expose content through selective citation rather than ranked retrieval.<n>We propose FeatGEO, a feature-level, multi-objective optimization framework that abstracts webpages into interpretable structural, content, and linguistic properties.
• Score: 3.3283145453561835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking [61.91472604294714]
  We propose a novel language dependency parsing mechanism to distill tracking principal components.<n>We exploit the powerful cross-modal understanding capability of the pre-trained vision-language model Qwen-VL.<n>Our method achieves consistent and superior tracking performance on multiple large-scale vision-language tracking benchmarks.
  arXiv  Detail & Related papers  (2026-06-28T12:12:18Z)
• From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning [18.351281487408176]
  Generative engines (GEs) are reshaping information access by replacing ranked links with citation-grounded answers.<n>We propose MAGEO, a multi-agent framework in which coordinated planning, editing, and fidelity-aware evaluation serve as the execution layer.<n>Experiments on three mainstream engines show MAGEO substantially outperforms baselines in both visibility and citation fidelity.
  arXiv  Detail & Related papers  (2026-04-21T14:39:24Z)
• Structural Feature Engineering for Generative Engine Optimization: How Content Structure Shapes Citation Behavior [3.433584969325024]
  We propose GEO-SFE, a systematic framework for structural feature engineering in generative engine optimization.<n>Our approach decomposes content structure into three hierarchical levels: macro-structure, meso-structure, and micro-structure.<n>We develop architecture-aware optimization strategies and predictive models that preserve semantic integrity while improving structural effectiveness.
  arXiv  Detail & Related papers  (2026-03-31T16:41:43Z)
• AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization [32.13915434333156]
  AgenticGEO is a self-evolving agentic framework formulating optimization as a content-conditioned control problem.<n>AgenticGEO achieves state-of-the-art performance and demonstrates robust transferability, outperforming 14 baselines across 3 datasets.
  arXiv  Detail & Related papers  (2026-03-02T16:13:13Z)
• Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets [54.06320619464273]
  Flow of SpanS (FOSS) is a principled GFlowNets framework for span generation.<n>FOSS constructs a dynamic span vocabulary by segmenting the retrieved text flexibly.<n>With specialized reward models, FoSS generates diverse, high-quality text.
  arXiv  Detail & Related papers  (2026-02-11T07:17:41Z)
• Caption Injection for Optimization in Generative Search Engine [15.472540238931202]
  Generative Search Engines (GSEs) leverage Retrieval-Augmented Generation (RAG) techniques and Large Language Models (LLMs)<n>We propose Caption Injection, the first multimodal G-SEO approach, which extracts captions from images and injects them into textual content.<n> Experimental results show that Caption Injection significantly outperforms text-only G-SEO baselines under the G-Eval metric.
  arXiv  Detail & Related papers  (2025-11-06T05:37:27Z)
• Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution [0.0]
  We propose a framework that integrates a memory-augmented Reflection RetrievalRAG module and a Self-Adaptive meta-controller.<n>REMO achieves more stable and robust tuning, albeit at the cost of increased computational overhead.
  arXiv  Detail & Related papers  (2025-08-26T07:25:45Z)
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models? [76.92519309816008]
  This paper investigates the influence of large language models (LLMs) on term-based retrieval models.<n>Our linguistic analysis reveals that LLM-generated texts exhibit smoother high-frequency and steeper low-frequency Zipf slopes.<n>Our study further explores whether term-based retrieval models demonstrate source bias, concluding that these models prioritize documents whose term distributions closely correspond to those of the queries.
  arXiv  Detail & Related papers  (2025-08-25T06:43:27Z)
• Discourse Features Enhance Detection of Document-Level Machine-Generated Content [53.41994768824785]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation.<n>Existing MGC detectors often focus solely on surface-level information, overlooking implicit and structural features.<n>We introduce novel methodologies and datasets to overcome these challenges.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback [50.84142264245052]
  This work introduces the Align-SLM framework to enhance the semantic understanding of textless Spoken Language Models (SLMs)<n>Our approach generates multiple speech continuations from a given prompt and uses semantic metrics to create preference data for Direct Preference Optimization (DPO)<n>We evaluate the framework using ZeroSpeech 2021 benchmarks for lexical and syntactic modeling, the spoken version of the StoryCloze dataset for semantic coherence, and other speech generation metrics, including the GPT4-o score and human evaluation.
  arXiv  Detail & Related papers  (2024-11-04T06:07:53Z)
• Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment [57.0121616203175]
  We propose FiSAO, a novel self-alignment method that utilizes the model's own visual encoder as a fine-grained verifier to improve vision-language alignment.<n>By leveraging token-level feedback from the vision encoder, FiSAO significantly improves vision-language alignment, even surpassing traditional preference tuning methods that require additional data.
  arXiv  Detail & Related papers  (2024-10-18T03:34:32Z)
• Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement [102.22911097049953]
  Large vision-language models (LVLMs) have achieved impressive results in visual question-answering and reasoning tasks.<n>Existing methods often depend on external models or data, leading to uncontrollable and unstable alignment results.<n>We propose SIMA, a self-improvement framework that enhances visual and language modality alignment without external dependencies.
  arXiv  Detail & Related papers  (2024-05-24T23:09:27Z)
• GEO: Generative Engine Optimization [50.45232692363787]
  We formalize the unified framework of generative engines (GEs) GEs use large language models (LLMs) to gather and summarize information to answer user queries. Generative Engines typically satisfy queries by synthesizing information from multiple sources and summarizing them. We introduce Generative Engine Optimization (GEO), the first novel paradigm to aid content creators in improving their content visibility in generative engine responses.
  arXiv  Detail & Related papers  (2023-11-16T10:06:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.