Pith. sign in

REVIEW 4 minor 95 references

The paper argues that GEO is not a single ranking task but a stochastic, partially observable pipeline, and that the field's most cited result—'up to 40% visibility gains'—is conditional on a document already being retrieved, not a general

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · deepseek-v4-flash

2026-08-02 02:56 UTC pith:KLWIT7FG

load-bearing objection A genuinely useful critical survey: it separates the conditional citation effect from the discovery/traffic claims in GEO, and the main soft spot is the unauditable corpus selection, not the synthesis itself.

arxiv 2607.14035 v1 pith:KLWIT7FG submitted 2026-07-15 cs.IR cs.DL

Optimizing Visibility in Generative Engines: A Critical Survey of Generative Engine Optimization (2023-2026)

Olivier Martinez This is my paper
classification cs.IR cs.DL
keywords generative engine optimizationGEOAI search visibilitycitation analysisalgorithmic auditingretrieval-augmented generationcausal measurementliterature survey
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This critical survey of 45 studies on Generative Engine Optimization (GEO) tries to establish what the field has actually proven, rather than what its promotional vocabulary suggests. The paper's central claim is that GEO operates across a multistage pipeline—from search activation, crawling, and retrieval, through reranking, generation, and citation, down to user behavior—and that treating visibility as one number obscures where interventions truly take effect. The widely cited 'up to 40%' gain from the foundational 2024 paper is real but narrowly scoped: it measures how much a document already placed in a five-source context gains in position-weighted citation share, not whether a page gets organically retrieved or whether it drives clicks. Across the reviewed corpus, the paper finds strong evidence that already-retrieved content can causally alter its citation or use, but no technique shows a stable, longitudinal, cross-platform causal effect on organic discoverability or downstream behavior. A sympathetic reader cares because this reframes GEO's promise: instead of a recipe for ranking highly in ChatGPT, the defendable science is about conditioning on retrieval, and the paper offers a visibility vector, an evidence hierarchy, and a measurement protocol to make that distinction operational.

Core claim

The core discovery is a scope restriction on what GEO can currently claim. The paper shows that the foundational 'up to 40%' figure derives from a simulator in which five documents are already placed in context, where one source's position-weighted word share (pawc) rises from 19.3 to 27.2 under a quotation-addition intervention—a relative gain of about 41%. It does not establish that a page will be retrieved organically, nor that it will generate traffic or conversions. The survey's synthesis of 45 studies concludes that within the reviewed corpus the evidence is narrow: already-retrieved content can causally influence an answer, including its rank, citation, or use, but no technique shows

What carries the argument

The central machinery is the visibility vector V_s = (D_s, K_s, C_s, P_s, H_s, F_s, B_s), which separates discoverability (retrieval probability), context exposure (rank, token allocation), citation probability, prominence (position, repetition), absorption (effective contribution to the answer's facts or language), fidelity (whether attributed claims are supported), and behavioral/economic outcome (click, referral, conversion). This vector is paired with a multistage formal model of the generative engine pipeline—activation, crawling/indexing, retrieval, reranking/context allocation, generation/citation, absorption/fidelity, and user behavior—and a causal estimand τ_T(m) that distinguishes

Load-bearing premise

The central absence claim—that no reviewed technique shows a stable, longitudinal, cross-platform causal effect on organic discoverability or downstream behavior—depends on the 45-study corpus being representative of the field; the paper itself notes that the original search did not retain database-specific hit counts or a complete exclusion ledger, and several key negative findings rely on preprints rather than peer-reviewed work.

What would settle it

A single preregistered randomized field experiment would falsify the paper's central absence claim if it showed: a specific, well-defined content intervention (e.g., adding verifiable structured data) that, across at least two major generative engines and over a period of months, durably increases organic retrieval probability (not just citation among already-retrieved sources) in a treated group compared to a randomized control, with a pre-specified primary metric and adequate statistical power.

Watch this falsifier. Get emailed when new claim-graph text bears on it.

If this is right

  • The 'up to 40%' GEO result should be read as a within-context effect, not a general promise of ranking highly in ChatGPT; it measures position-weighted attribution share for a document already placed in a fixed, five-source context.
  • Generic GEO heuristics—such as keyword stuffing, fluency rewrites, or formatting tricks—do not generalize; the most reproducible levers are query–document relevance and context position, which shift attention upstream toward retrieval.
  • Optimizing for citation can backfire on retrieval: the SAGEO Arena experiment shows that body-only rewrites reduce average top-20 presence by ~9%, top-10 presence after reranking by ~16%, and final citation by ~6%.
  • Commercial engines are heterogeneous and unstable: audits find low source overlap across engines, substantial run-to-run variability (daily Jaccard scores ~0.34–0.42), and persistent fidelity gaps, so visibility must be measured as a distribution over engines, dates, and paraphrases, not a point estimate.
  • Evidence for traffic or conversion effects is the weakest link: only one suggestive quasi-experiment (an estimated multiplier of 1.82 with a placebo p = 0.16) and one under-specified industry report claim production-level traffic lifts, falling short of causal standards.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the survey's absence claim holds, a practical consequence is that GEO budgets should be redirected toward retrievability and content quality rather than citation-optimization tricks, because a page that is never retrieved cannot benefit from any downstream effect.
  • The recognition–discovery gap documented for named products (99.4% recognition vs 3.32% organic discovery for ChatGPT) implies that brand authority, third-party coverage, and entity-level representation may matter more than page-level rewrites, suggesting a network-level view of GEO rather than a page-level one.
  • A testable extension the paper leaves implicit: a randomized field trial across multiple engines with controlled pages, measuring organic retrieval probability (not just citation given retrieval) over several months, could directly falsify the central absence claim if a positive, stable effect emerges.
  • The paper's proposed evidence hierarchy and multi-stage measurement protocol could be adopted more broadly by researchers auditing algorithmic surfaces beyond GEO, offering a template for separating conditional from total effects in any black-box optimization context.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

0 major / 4 minor

Summary. This manuscript is a critical scoping review of 45 studies on Generative Engine Optimization (GEO) published between November 2023 and July 2026. It formalizes GEO as a multistage, partially observable pipeline (activation, retrieval, reranking, generation, citation, absorption, fidelity, downstream behavior), introduces a visibility vector and an evidence hierarchy, and proposes a reproducibility protocol. The paper's central claims are that the widely cited 'up to 40%' result of Aggarwal et al. is a within-context relative gain in position-adjusted word count, that the surveyed literature supports causal effects only for already-retrieved content, and that no reviewed technique shows a stable, longitudinal, cross-platform causal effect on organic discoverability or downstream behavior. It also synthesizes commercial audits, manipulation/defense work, and governance considerations.

Significance. The paper's main strength is its careful epistemic calibration. It correctly separates peer-reviewed studies from preprints (Section 2.3), distinguishes conditional from total effects (Section 3.3), and explicitly bounds its absence claims to the reviewed corpus (Abstract; Section 2.4; Section 15). The reading of the foundational paper's 41% figure as a within-context relative pawc gain is accurate and well documented (Table 1, Section 4.1). The proposed visibility vector, evidence hierarchy (Appendix A), and factorial measurement protocol are useful contributions that can discipline future work in this rapidly growing area. If the synthesis is accepted, it materially corrects the overreading of GEO's promise and redirects attention to retrieval-stage and downstream-outcome measurement. The principal limitation is the unaudited completeness of the corpus: because the negative claim is explicitly corpus-relative, the issue is a constraint on external generalization rather than an internal inconsistency.

minor comments (4)
  1. [Abstract, Section 10, Table 5] The manuscript is careful to bound the negative claim with 'Within this corpus' in the Abstract and Section 15, but Section 10's opening synthesis ('The most important conclusion concerns scope...') and the confidence ratings in Table 5 do not repeat that qualifier. Since Section 2.4 concedes that database-specific hit counts and the complete exclusion ledger were not retained, a reader could over-generalize the absence claim. Please add 'within the reviewed corpus' to Table 5's header or a footnote, and to the first sentence of Section 10, so the epistemic scope is uniform throughout.
  2. [Section 11.3, Equation (8)] The proposed hierarchical model has an indexing inconsistency: the outcome is indexed by i, q, e, t, r, but the treatment indicator is T_i and the random effect is b_s. Since the source is the treatment unit, the equation should use T_s (or clarify what i denotes). Please also state whether b_q, b_e, b_t, and b_s are crossed or nested, and define the cluster structure explicitly.
  3. [Section 6.2] The recommendation of 'seven to eight repetitions as a starting point' is appropriately hedged, but 'the appropriate practice is sequential precision analysis' needs an operational stopping rule. Specify a concrete criterion (e.g., continue until the half-width of the confidence interval is below a prespecified threshold) or give an example so that readers can implement it.
  4. [Appendix B, Table 8] The entry for Nimase et al. 2026 ('GEO-Bench') shares a name with the original benchmark used by Aggarwal et al. 2024. This is a source of potential confusion. Please add a disambiguating note, for example 'not the original GEO-Bench benchmark,' in the table or in the text.

Circularity Check

0 steps flagged

No circularity: conclusions are external assessments of a reviewed corpus, not consequences of the paper's own definitions.

full rationale

The paper is a critical survey, not a fitted model. Its central formal objects—Eq. (5) visibility vector, Eq. (6) causal estimand, Eq. (7) activation/retrieval/citation decomposition, and Table 7 evidence hierarchy—are definitions, identities, or proposed grading standards rather than load-bearing derivations whose conclusions equal their inputs. The headline conclusion ('Within this corpus, the evidence is narrow: already-retrieved content can causally alter its citation or use, but no reviewed technique shows a stable, longitudinal, cross-platform causal effect...') is explicit about its corpus-bound scope and is justified by citations to external peer-reviewed work, preprints, and audits. The paper does not fit parameters and then relabel them as predictions, nor does it invoke any uniqueness theorem or prior result by the same author to make its choice forced. There are no self-citations at all. The acknowledgments in §2.4 and §14 that hit counts and the exclusion ledger were not retained affect external validity and reproducibility, not circularity: a corpus-completeness limitation is an epistemic caveat, not a self-referential derivation. The proposed evidence hierarchy is used as a lens for grading other studies, but the survey's conclusions do not reduce to that hierarchy; they rest on the reported empirical findings of the 45 studies. No circular step meeting the quoted-evidence standard is present.

Axiom & Free-Parameter Ledger

0 free parameters · 4 axioms · 0 invented entities

No free parameters are fitted: the paper reports no new experiments. The axioms are the modeling and selection assumptions that underlie the review's synthetic conclusions. The visibility vector (Eq. 5) is a measurement abstraction, not an invented physical entity, so it is not listed as an invented entity.

axioms (4)
  • domain assumption The generative visibility pipeline is faithfully decomposed into activation, retrieval, reranking, generation, citation, absorption, and behavior stages (Eqs. 1-6).
    The entire review's framework, visibility vector, and protocol rest on this staged decomposition being the right abstraction. It is a modeling choice argued from the literature, not derived or validated against a benchmark in this paper.
  • domain assumption The 45-study corpus is representative of GEO research and relevant RAG/evaluation work in the November 2023-July 2026 window.
    The headline absence claim ('no reviewed technique shows...') is only meaningful if selection is unbiased. §2.4 concedes that database-specific hit counts and a complete exclusion ledger were not retained, so representativeness is asserted rather than demonstrated.
  • domain assumption LLM judges are circular unless the generator and judge model families are separated, the judge is blinded and human-validated (§6.4).
    The review applies this methodological standard to grade the evidence of other studies. It is a defensible position argued from the literature, but it is an evaluation axiom the paper does not itself prove.
  • ad hoc to paper The evidence hierarchy (Appendix A, Table 7) is the correct lens for grading GEO claims.
    This five-level grading scheme is introduced by this paper and then used to assess the field's claims. It is a reasonable construct, but the review's confidence table (Table 5) inherits its structure from this self-authored standard.

pith-pipeline@v1.3.0-alltime-deepseek · 174 in / 13988 out tokens · 147009 ms · 2026-08-02T02:56:22.603668+00:00 · methodology

0 comments
read the original abstract

Generative Engine Optimization (GEO) seeks to increase content's presence, likelihood of citation, or influence in answers produced by generative engines. Since the foundational GEO paper, the field has expanded rapidly, but terminology, metrics, and evidence standards remain heterogeneous. This critical survey reviews 45 studies selected under a November 2023-July 2026 publication window, including one earlier preprint published at EMNLP after the window opened, plus relevant RAG and evaluation work. We argue that GEO is not a single ranking task but a stochastic, partially observable pipeline spanning search activation, crawling and indexing, retrieval, reranking and context allocation, citation, prominence, factual absorption, fidelity, and user behavior. The foundational paper's widely cited gains are valid within its experimental setting but conditional on a source already being present in a fixed context; they establish neither organic discoverability nor durable traffic effects. Reviewed work indicates that topical relevance and context position are the most reproducible levers, generic heuristics transfer poorly, competition can erode individual gains, and citation-oriented rewrites can impair retrieval. Commercial audits further reveal low source overlap, substantial run-to-run variability, and persistent fidelity gaps. We contribute a multistage formal model, a visibility vector separating discoverability, citation, absorption, and economic outcomes, an evidence hierarchy, and a reproducible protocol based on repeated measurements, paraphrases, controls, human validation, and multi-actor interference. Within this corpus, the evidence is narrow: already-retrieved content can causally alter its citation or use, but no reviewed technique shows a stable, longitudinal, cross-platform causal effect on organic discoverability or downstream behavior.

Figures

Figures reproduced from arXiv: 2607.14035 by Olivier Martinez.

Figure 1
Figure 1. Figure 1: The causal visibility pipeline. Most GEO studies optimize the stages between context allocation and [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

95 extracted references · 9 canonical work pages

  1. [1]

    GEO : Generative engine optimization

    Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, and Ameet Deshpande. GEO : Generative engine optimization. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 5--16, 2024. doi:10.1145/3637528.3671900. URL https://doi.org/10.1145/3637528.3671900

    arXiv 2024

  2. [2]

    Synthetic sources? auditing generative search engine citations for evidence of AI -generated sources, 2026

    Mowafak Allaham and Nicholas Diakopoulos. Synthetic sources? auditing generative search engine citations for evidence of AI -generated sources, 2026. URL https://arxiv.org/abs/2605.23684

    Pith/arXiv arXiv 2026

  3. [3]

    Bagga, Vivek F

    Puneet S. Bagga, Vivek F. Farias, Tamar Korkotashvili, Tianyi Peng, and Yuhang Wu. E-GEO : A testbed for generative engine optimization in e-commerce, 2025. URL https://arxiv.org/abs/2511.20867

    Pith/arXiv arXiv 2025

  4. [4]

    Generative engine optimization: How to dominate AI search, 2025 a

    Mahe Chen, Xiaoxuan Wang, Kaiwen Chen, and Nick Koudas. Generative engine optimization: How to dominate AI search, 2025 a . URL https://arxiv.org/abs/2509.08919

    Pith/arXiv arXiv 2025

  5. [5]

    CC-GSEO-Bench : A content-centric benchmark for measuring source influence in generative search engines, 2025 b

    Qiyuan Chen, Jiahe Chen, Hongsen Huang, Qian Shao, Jintai Chen, Renjie Hua, Hongxia Xu, Ruijia Wu, Chuan Ren, and Jian Wu. CC-GSEO-Bench : A content-centric benchmark for measuring source influence in generative search engines, 2025 b . URL https://arxiv.org/abs/2509.05607

    arXiv 2025

  6. [6]

    Mind reader: Latent user demand-guided content optimization for generative search engine

    Tong Chen, JiaWei Guo, Yuxi Li, Baiming Chen, Houxing Ren, Zhiwei Zhang, Yunxiang Zhang, Hanyang Xia, Kun Liang, and Zhaoran Fan. Mind reader: Latent user demand-guided content optimization for generative search engine. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, pages 40832--40848, 2026. doi:10.18653/v1/202...

    work page doi:10.18653/v1/2026.acl-long.1894 2026

  7. [7]

    Chen, Mike Smith, Cristian Borcea, and Yi Chen

    Riley Grossman, Songjiang Liu, Michael K. Chen, Mike Smith, Cristian Borcea, and Yi Chen. How generative AI disrupts search: An empirical study of google search, gemini, and AI overviews. Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2026. URL https://arxiv.org/abs/2604.27790. Forthcoming ...

    Pith/arXiv arXiv 2026

  8. [8]

    Rewrite-to-rank: Optimizing ad visibility via retrieval-aware text rewriting, 2025

    Chloe Ho, Ishneet Sukhvinder Singh, Diya Sharma, Tanvi Reddy Anumandla, Michael Lu, Vasu Sharma, and Kevin Zhu. Rewrite-to-rank: Optimizing ad visibility via retrieval-aware text rewriting, 2025. URL https://arxiv.org/abs/2507.21099. ICML 2025 workshop

    Pith/arXiv arXiv 2025

  9. [9]

    Dynamics of adversarial attacks on large language model-based search engines, 2025

    Xiyang Hu. Dynamics of adversarial attacks on large language model-based search engines, 2025. URL https://arxiv.org/abs/2501.00745. ICML 2026 workshop version

    Pith/arXiv arXiv 2025

  10. [10]

    Answer bubbles: Information exposure in AI -mediated search, 2026

    Michelle Huang, Agam Goyal, Koustuv Saha, and Eshwar Chandrasekharan. Answer bubbles: Information exposure in AI -mediated search, 2026. URL https://arxiv.org/abs/2603.16138

    arXiv 2026

  11. [11]

    Controlling output rankings in generative engines for LLM -based search, 2026

    Haibo Jin, Ruoxi Chen, Peiyan Zhang, Yifeng Luo, Huimin Zeng, Man Luo, and Haohan Wang. Controlling output rankings in generative engines for LLM -based search, 2026. URL https://arxiv.org/abs/2602.03608

    arXiv 2026

  12. [12]

    SAGEO Arena : A realistic environment for evaluating search-augmented generative engine optimization, 2026

    Sunghwan Kim, Wooseok Jeong, Serin Kim, Sangam Lee, and Dongha Lee. SAGEO Arena : A realistic environment for evaluating search-augmented generative engine optimization, 2026. URL https://arxiv.org/abs/2602.12187

    arXiv 2026

  13. [13]

    Gummadi, and Muhammad Bilal Zafar

    Elisabeth Kirsten, Jost Große Perdekamp, Qinyuan Wu, Mihir Upadhyay, Krishna P. Gummadi, and Muhammad Bilal Zafar. Characterizing web search in the age of generative AI . In Findings of the Association for Computational Linguistics: ACL 2026, pages 10827--10848, 2026. doi:10.18653/v1/2026.findings-acl.526. URL https://aclanthology.org/2026.findings-acl.526/

    work page doi:10.18653/v1/2026.findings-acl.526 2026

  14. [14]

    Manipulating large language models to increase product visibility, 2024

    Aounon Kumar and Himabindu Lakkaraju. Manipulating large language models to increase product visibility, 2024. URL https://arxiv.org/abs/2404.07981

    Pith/arXiv arXiv 2024

  15. [15]

    Retrieval-augmented generation for knowledge-intensive NLP tasks

    Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems, volume 33, pages 9459--9474, 2020. URL https://...

    2020

  16. [16]

    Generative AI search engines as arbiters of public knowledge: An audit of bias and authority

    Alice Li and Luanne Sinnamon. Generative AI search engines as arbiters of public knowledge: An audit of bias and authority. Proceedings of the Association for Information Science and Technology, 61 0 (1): 0 205--217, 2024. doi:10.1002/pra2.1021. URL https://doi.org/10.1002/pra2.1021

    doi:10.1002/pra2.1021 2024

  17. [17]

    Liu, Tianyi Zhang, and Percy Liang

    Nelson F. Liu, Tianyi Zhang, and Percy Liang. Evaluating verifiability in generative search engines. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7001--7025, 2023 a . doi:10.18653/v1/2023.findings-emnlp.467. URL https://aclanthology.org/2023.findings-emnlp.467/

    doi:10.18653/v1/2023.findings-emnlp.467 2023

  18. [18]

    G-Eval : NLG evaluation using GPT-4 with better human alignment

    Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, and Chenguang Zhu. G-Eval : NLG evaluation using GPT-4 with better human alignment. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2511--2522, 2023 b . doi:10.18653/v1/2023.emnlp-main.153. URL https://aclanthology.org/2023.emnlp-main.153/

    doi:10.18653/v1/2023.emnlp-main.153 2023

  19. [19]

    Think before writing: Feature-level multi-objective optimization for generative citation visibility

    Zikang Liu and Peilan Xu. Think before writing: Feature-level multi-objective optimization for generative citation visibility. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, pages 20290--20303, 2026. doi:10.18653/v1/2026.acl-long.929. URL https://aclanthology.org/2026.acl-long.929/

    work page doi:10.18653/v1/2026.acl-long.929 2026

  20. [20]

    Beyond SEO : A transformer-based approach for reinventing web content optimisation, 2025

    Florian Lüttgenau, Imar Colic, and Gervasio Ramirez. Beyond SEO : A transformer-based approach for reinventing web content optimisation, 2025. URL https://arxiv.org/abs/2507.03169

    Pith/arXiv arXiv 2025

  21. [21]

    Adversarial search engine optimization for large language models

    Fredrik Nestaas, Edoardo Debenedetti, and Florian Tramèr. Adversarial search engine optimization for large language models. In International Conference on Learning Representations, 2025. URL https://openreview.net/forum?id=hkdqxN3c7t

    2025

  22. [22]

    GEO-Bench : Benchmarking ranking manipulation in generative engine optimization, 2026

    Ojas Nimase, Zhe Chen, Gengpei Qi, Yue Zhao, and Xiyang Hu. GEO-Bench : Benchmarking ranking manipulation in generative engine optimization, 2026. URL https://arxiv.org/abs/2605.29107

    Pith/arXiv arXiv 2026

  23. [23]

    Ranking manipulation for conversational search engines

    Samuel Pfrommer, Yatong Bai, Tanmay Gautam, and Somayeh Sojoudi. Ranking manipulation for conversational search engines. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9523--9552, 2024. doi:10.18653/v1/2024.emnlp-main.534. URL https://aclanthology.org/2024.emnlp-main.534/

    work page doi:10.18653/v1/2024.emnlp-main.534 2024

  24. [24]

    C-SEO Bench : Does conversational SEO work? In Advances in Neural Information Processing Systems 38: Datasets and Benchmarks Track, 2025

    Haritz Puerto, Martin Gubri, Tommaso Green, Seong Joon Oh, and Sangdoo Yun. C-SEO Bench : Does conversational SEO work? In Advances in Neural Information Processing Systems 38: Datasets and Benchmarks Track, 2025. URL https://proceedings.neurips.cc/paper_files/paper/2025/hash/27aa3aeff0f8460a7b43d30fa6c5c032-Abstract-Datasets_and_Benchmarks_Track.html

    2025

  25. [25]

    The ranking blind spot: Decision hijacking in LLM -based text ranking

    Yaoyao Qian, Yifan Zeng, Yuchao Jiang, Chelsi Jain, and Huazheng Wang. The ranking blind spot: Decision hijacking in LLM -based text ranking. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 21958--21968, 2025. doi:10.18653/v1/2025.emnlp-main.1116. URL https://aclanthology.org/2025.emnlp-main.1116/

    work page doi:10.18653/v1/2025.emnlp-main.1116 2025

  26. [26]

    Don't measure once: Measuring visibility in AI search ( GEO ), 2026

    Julius Schulte, Malte Bleeker, and Philipp Kaufmann. Don't measure once: Measuring visibility in AI search ( GEO ), 2026. URL https://arxiv.org/abs/2604.07585

    Pith/arXiv arXiv 2026

  27. [27]

    The discovery gap: How product hunt startups vanish in LLM organic discovery queries, 2026

    Amit Prakash Sharma. The discovery gap: How product hunt startups vanish in LLM organic discovery queries, 2026. URL https://arxiv.org/abs/2601.00912

    arXiv 2026

  28. [28]

    Exploring LLM biases to manipulate AI search overview, 2026

    Roman Smirnov. Exploring LLM biases to manipulate AI search overview, 2026. URL https://arxiv.org/abs/2605.00012

    Pith/arXiv arXiv 2026

  29. [29]

    StealthRank : LLM ranking manipulation via stealthy prompt optimization, 2025

    Yiming Tang, Yi Fan, Chenxiao Yu, Tiankai Yang, Yue Zhao, and Xiyang Hu. StealthRank : LLM ranking manipulation via stealthy prompt optimization, 2025. URL https://arxiv.org/abs/2504.05804. ICML 2026 workshop version

    Pith/arXiv arXiv 2025

  30. [30]

    Diagnosing and repairing citation failures in generative engine optimization, 2026

    Zhihua Tian, Yuhan Chen, Yao Tang, Jian Liu, and Ruoxi Jia. Diagnosing and repairing citation failures in generative engine optimization, 2026. URL https://arxiv.org/abs/2603.09296

    arXiv 2026

  31. [31]

    Search engines in the AI era: A qualitative understanding to the false promise of factual and verifiable source-cited responses in LLM -based search

    Pranav Narayanan Venkit, Philippe Laban, Yilun Zhou, Yixin Mao, and Chien-Sheng Wu. Search engines in the AI era: A qualitative understanding to the false promise of factual and verifiable source-cited responses in LLM -based search. In Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, pages 1325--1340, 2025. doi:10.114...

    arXiv 2025

  32. [33]

    Assessing web search credibility and response groundedness in chat assistants

    Ivan Vykopal, Mat \'u s Pikuliak, Simon Ostermann, and Mari \'a n S imko. Assessing web search credibility and response groundedness in chat assistants. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, pages 2539--2560, 2026. doi:10.18653/v1/2026.eacl-long.115. URL https://aclanthology.org/202...

    work page doi:10.18653/v1/2026.eacl-long.115 2026

  33. [34]

    What evidence do language models find convincing? In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pages 7468--7484, 2024

    Alexander Wan, Eric Wallace, and Dan Klein. What evidence do language models find convincing? In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pages 7468--7484, 2024. doi:10.18653/v1/2024.acl-long.403. URL https://aclanthology.org/2024.acl-long.403/

    doi:10.18653/v1/2024.acl-long.403 2024

  34. [35]

    Disentangling answer engine optimization from platform growth: A log-based natural experiment on chatgpt referral traffic, 2026

    Keisuke Watanabe and Kazuki Nakayashiki. Disentangling answer engine optimization from platform growth: A log-based natural experiment on chatgpt referral traffic, 2026. URL https://arxiv.org/abs/2606.04362

    Pith/arXiv arXiv 2026

  35. [36]

    Position: Generative engine optimization creates underexamined risks, governance must target concentration, disclosure, and academic blind spots

    Yizhu Wen, Nan Zhang, Haohan Yuan, Xun Chen, Haopeng Zhang, and Hanqing Guo. Position: Generative engine optimization creates underexamined risks, governance must target concentration, disclosure, and academic blind spots. In Proceedings of the 43rd International Conference on Machine Learning: Position Paper Track, 2026. URL https://arxiv.org/abs/2606.12439

    Pith/arXiv arXiv 2026

  36. [37]

    From experience to skill: Multi-agent generative engine optimization via reusable strategy learning

    Beining Wu, Fuyou Mao, Jiong Lin, Cheng Yang, Jiaxuan Lu, Yifu Guo, Siyu Zhang, Yifan Wu, Ying Huang, and Fu Li. From experience to skill: Multi-agent generative engine optimization via reusable strategy learning. In Findings of the Association for Computational Linguistics: ACL 2026, pages 43305--43315, 2026 a . doi:10.18653/v1/2026.findings-acl.2149. UR...

    work page doi:10.18653/v1/2026.findings-acl.2149 2026

  37. [38]

    Do AI overviews benefit search engines? an ecosystem perspective, 2026 b

    Yihang Wu, Jiajun Tang, Jinfei Liu, Haifeng Xu, and Fan Yao. Do AI overviews benefit search engines? an ecosystem perspective, 2026 b . URL https://arxiv.org/abs/2601.22493

    arXiv 2026

  38. [39]

    What generative search engines like and how to optimize web content cooperatively

    Yujiang Wu, Shanshan Zhong, Yubin Kim, and Chenyan Xiong. What generative search engines like and how to optimize web content cooperatively. In The Fourteenth International Conference on Learning Representations, 2026 c . URL https://iclr.cc/virtual/2026/poster/10010153

    arXiv 2026

  39. [40]

    Do RAG systems cover what matters? evaluating and optimizing responses with sub-question coverage

    Kaige Xie, Philippe Laban, Prafulla Kumar Choubey, Caiming Xiong, and Chien-Sheng Wu. Do RAG systems cover what matters? evaluating and optimizing responses with sub-question coverage. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, pages 5836--5849, 2025. doi:10.18653/v1/2025....

    doi:10.18653/v1/2025.naacl-long.301 2025

  40. [41]

    Are LLM s reliable rankers? rank manipulation via two-stage token optimization

    Tiancheng Xing, Jerry Li, Yixuan Du, and Xiyang Hu. Are LLM s reliable rankers? rank manipulation via two-stage token optimization. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, pages 9120--9132, 2026. doi:10.18653/v1/2026.acl-long.413. URL https://aclanthology.org/2026.acl-long.413/

    work page doi:10.18653/v1/2026.acl-long.413 2026

  41. [42]

    Montgomery

    Haofei Xu, Umar Iqbal, and Jacob M. Montgomery. Measuring google AI overviews: Activation, source quality, claim fidelity, and publisher impact, 2026. URL https://arxiv.org/abs/2605.14021

    Pith/arXiv arXiv 2026

  42. [43]

    Structural feature engineering for generative engine optimization: How content structure shapes citation behavior, 2026

    Junwei Yu, Mufeng Yang, Yepeng Ding, and Hiroyuki Sato. Structural feature engineering for generative engine optimization: How content structure shapes citation behavior, 2026. URL https://arxiv.org/abs/2603.29979

    arXiv 2026

  43. [44]

    AgenticGEO : A self-evolving agentic system for generative engine optimization, 2026

    Jiaqi Yuan, Jialu Wang, Zihan Wang, Qingyun Sun, Ruijie Wang, and Jianxin Li. AgenticGEO : A self-evolving agentic system for generative engine optimization, 2026. URL https://arxiv.org/abs/2603.20213

    arXiv 2026

  44. [45]

    Generative engine optimization: A VLM and agent framework for pinterest acquisition growth, 2026 a

    Faye Zhang, Qianyu Cheng, Jasmine Wan, Vishwakarma Singh, Jinfeng Rao, and Kofi Boakye. Generative engine optimization: A VLM and agent framework for pinterest acquisition growth, 2026 a . URL https://arxiv.org/abs/2602.02961

    arXiv 2026

  45. [46]

    From citation selection to citation absorption: A measurement framework for generative engine optimization across AI search platforms, 2026 b

    Kai Zhang, Xinyue He, and Jingang Yao. From citation selection to citation absorption: A measurement framework for generative engine optimization across AI search platforms, 2026 b . URL https://arxiv.org/abs/2604.25707

    Pith/arXiv arXiv 2026

  46. [47]

    GRADA : Graph-based reranking against adversarial documents attack

    Jingjie Zheng, Aryo Pradipta Gema, Giwon Hong, Xuanli He, Pasquale Minervini, Youcheng Sun, and Qiongkai Xu. GRADA : Graph-based reranking against adversarial documents attack. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 22244--22266, 2025. doi:10.18653/v1/2025.emnlp-main.1132. URL https://aclanthology....

    doi:10.18653/v1/2025.emnlp-main.1132 2025

  47. [48]

    IF-GEO : Conflict-aware instruction fusion for multi-query generative engine optimization

    Heyang Zhou, Jiajia Chen, Xiaolu Chen, Jie Bao, Zhen Chen, and Yong Liao. IF-GEO : Conflict-aware instruction fusion for multi-query generative engine optimization. In Findings of the Association for Computational Linguistics: ACL 2026, pages 27576--27590, 2026. doi:10.18653/v1/2026.findings-acl.1373. URL https://aclanthology.org/2026.findings-acl.1373/

    work page doi:10.18653/v1/2026.findings-acl.1373 2026

  48. [49]

    Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , pages =

    Pranjal Aggarwal and Vishvak Murahari and Tanmay Rajpurohit and Ashwin Kalyan and Karthik Narasimhan and Ameet Deshpande , title =. Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , pages =. 2024 , doi =

    2024

  49. [50]

    Liu and Tianyi Zhang and Percy Liang , title =

    Nelson F. Liu and Tianyi Zhang and Percy Liang , title =. Findings of the Association for Computational Linguistics: EMNLP 2023 , pages =. 2023 , doi =

    2023

  50. [51]

    Proceedings of the Association for Information Science and Technology , volume =

    Alice Li and Luanne Sinnamon , title =. Proceedings of the Association for Information Science and Technology , volume =. 2024 , doi =

    2024

  51. [52]

    Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics , pages =

    Alexander Wan and Eric Wallace and Dan Klein , title =. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics , pages =. 2024 , doi =

    2024

  52. [53]

    2024 , eprint =

    Aounon Kumar and Himabindu Lakkaraju , title =. 2024 , eprint =

    2024

  53. [54]

    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages =

    Samuel Pfrommer and Yatong Bai and Tanmay Gautam and Somayeh Sojoudi , title =. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages =. 2024 , doi =

    2024

  54. [55]

    International Conference on Learning Representations , year =

    Fredrik Nestaas and Edoardo Debenedetti and Florian Tramèr , title =. International Conference on Learning Representations , year =

  55. [56]

    Advances in Neural Information Processing Systems 38: Datasets and Benchmarks Track , year =

    Haritz Puerto and Martin Gubri and Tommaso Green and Seong Joon Oh and Sangdoo Yun , title =. Advances in Neural Information Processing Systems 38: Datasets and Benchmarks Track , year =

  56. [57]

    The Fourteenth International Conference on Learning Representations , year =

    Yujiang Wu and Shanshan Zhong and Yubin Kim and Chenyan Xiong , title =. The Fourteenth International Conference on Learning Representations , year =

  57. [58]

    2025 , eprint =

    Qiyuan Chen and Jiahe Chen and Hongsen Huang and Qian Shao and Jintai Chen and Renjie Hua and Hongxia Xu and Ruijia Wu and Chuan Ren and Jian Wu , title =. 2025 , eprint =

    2025

  58. [59]

    2026 , eprint =

    Sunghwan Kim and Wooseok Jeong and Serin Kim and Sangam Lee and Dongha Lee , title =. 2026 , eprint =

    2026

  59. [60]

    Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics , pages =

    Zikang Liu and Peilan Xu , title =. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics , pages =. 2026 , doi =

    2026

  60. [61]

    Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics , pages =

    Tong Chen and JiaWei Guo and Yuxi Li and Baiming Chen and Houxing Ren and Zhiwei Zhang and Yunxiang Zhang and Hanyang Xia and Kun Liang and Zhaoran Fan , title =. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics , pages =. 2026 , doi =

    2026

  61. [62]

    Findings of the Association for Computational Linguistics: ACL 2026 , pages =

    Heyang Zhou and Jiajia Chen and Xiaolu Chen and Jie Bao and Zhen Chen and Yong Liao , title =. Findings of the Association for Computational Linguistics: ACL 2026 , pages =. 2026 , doi =

    2026

  62. [63]

    Findings of the Association for Computational Linguistics: ACL 2026 , pages =

    Beining Wu and Fuyou Mao and Jiong Lin and Cheng Yang and Jiaxuan Lu and Yifu Guo and Siyu Zhang and Yifan Wu and Ying Huang and Fu Li , title =. Findings of the Association for Computational Linguistics: ACL 2026 , pages =. 2026 , doi =

    2026

  63. [64]

    2026 , eprint =

    Zhihua Tian and Yuhan Chen and Yao Tang and Jian Liu and Ruoxi Jia , title =. 2026 , eprint =

    2026

  64. [65]

    2026 , eprint =

    Jiaqi Yuan and Jialu Wang and Zihan Wang and Qingyun Sun and Ruijie Wang and Jianxin Li , title =. 2026 , eprint =

    2026

  65. [66]

    Bagga and Vivek F

    Puneet S. Bagga and Vivek F. Farias and Tamar Korkotashvili and Tianyi Peng and Yuhang Wu , title =. 2025 , eprint =

    2025

  66. [67]

    Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval , year =

    Rahul Vishwakarma and Shushant Kumar and Ratnesh Jamidar , title =. Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval , year =. doi:10.1145/3805712.3808445 , url =

    arXiv

  67. [68]

    2026 , eprint =

    Kai Zhang and Xinyue He and Jingang Yao , title =. 2026 , eprint =

    2026

  68. [69]

    Gummadi and Muhammad Bilal Zafar , title =

    Elisabeth Kirsten and Jost Große Perdekamp and Qinyuan Wu and Mihir Upadhyay and Krishna P. Gummadi and Muhammad Bilal Zafar , title =. Findings of the Association for Computational Linguistics: ACL 2026 , pages =. 2026 , doi =

    2026

  69. [70]

    Chen and Mike Smith and Cristian Borcea and Yi Chen , title =

    Riley Grossman and Songjiang Liu and Michael K. Chen and Mike Smith and Cristian Borcea and Yi Chen , title =. Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval , year =

  70. [71]

    Montgomery , title =

    Haofei Xu and Umar Iqbal and Jacob M. Montgomery , title =. 2026 , eprint =

    2026

  71. [72]

    2026 , eprint =

    Mowafak Allaham and Nicholas Diakopoulos , title =. 2026 , eprint =

    2026

  72. [73]

    2026 , eprint =

    Julius Schulte and Malte Bleeker and Philipp Kaufmann , title =. 2026 , eprint =

    2026

  73. [74]

    2026 , eprint =

    Michelle Huang and Agam Goyal and Koustuv Saha and Eshwar Chandrasekharan , title =. 2026 , eprint =

    2026

  74. [75]

    Assessing Web Search Credibility and Response Groundedness in Chat Assistants , booktitle =

    Ivan Vykopal and Mat. Assessing Web Search Credibility and Response Groundedness in Chat Assistants , booktitle =. 2026 , doi =

    2026

  75. [76]

    Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency , pages =

    Pranav Narayanan Venkit and Philippe Laban and Yilun Zhou and Yixin Mao and Chien-Sheng Wu , title =. Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency , pages =. 2025 , doi =

    2025

  76. [77]

    2026 , eprint =

    Keisuke Watanabe and Kazuki Nakayashiki , title =. 2026 , eprint =

    2026

  77. [78]

    2026 , eprint =

    Amit Prakash Sharma , title =. 2026 , eprint =

    2026

  78. [79]

    Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages =

    Yaoyao Qian and Yifan Zeng and Yuchao Jiang and Chelsi Jain and Huazheng Wang , title =. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages =. 2025 , doi =

    2025

  79. [80]

    Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics , pages =

    Tiancheng Xing and Jerry Li and Yixuan Du and Xiyang Hu , title =. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics , pages =. 2026 , doi =

    2026

  80. [81]

    Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages =

    Jingjie Zheng and Aryo Pradipta Gema and Giwon Hong and Xuanli He and Pasquale Minervini and Youcheng Sun and Qiongkai Xu , title =. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages =. 2025 , doi =

    2025

Showing first 80 references.