# GroundedGEO: Auditing the Evidence Gap in Generative Search Rankings

arXiv: https://arxiv.org/abs/2609.25189 · HTML: https://mlsanity.com/paper/2609.25189/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents](https://mlsanity.com/paper/2605.12887/) (2026)
- [SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization](https://mlsanity.com/paper/2605.21948/) (2026)
- [When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization](https://mlsanity.com/paper/2609.02964/) (2026)
- [Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning](https://mlsanity.com/paper/2609.06027/) (2026)

## Abstract (arXiv)

Generative search systems rank products and services for consequential decisions, and publishers can cheaply make candidate text look relevant. Yet evidence status is not a text property but a claim-evidence relation: text-only rankers and defenses cannot separate honest detailed content from fabricated detail, creating an identifiability gap. We audit this gap with an evidence-paired benchmark (50 e-commerce queries, 1,950 cases) and a claim-level reranker, GroundedGEO, that penalizes query-relevant claims lacking support in a supplied packet. Matched rich variants control format and volume; packet twins add attestations at fixed text, while thinned packets withdraw them. On the frozen listwise ranker Qwen2.5-7B, unsupported-rich variants show significant normalized rank gain over clean candidates (+0.065 to +0.092 across claim profiles, Holm-corrected), while supported and neutral controls do not; the effect is model-dependent (marginal on MiMo-v2.5, absent on GLM-5.3-Flash). On a frozen pointwise scorer, oracle evidence labels cut the unsupported-rich top-3 rate from 0.65 to 0.43 (laundering from 0.61 to 0.39) at lambda=40 with zero false suppression; packet twins restore the original rates without changing text. Against a 370-claim human gold, all tested automatic judges fail the preregistered reliability gate, although the best local judge retains 79-100% of oracle suppression with zero measured false suppression on protected arms. Separately, stripping attestation coverage increases false suppression by 0.307. These diagnostic effects identify two limits on the evidence channel: label quality and packet coverage. They do not validate an automatic defense, and interpretation of the adverse human-gold arm remains pending adjudication.