sisalto/vaitteet/geo-optimointi-tutkimus.yaml
Artikkelin geo-optimointi-tutkimus lainaukset. Tämä on repon tiedosto sellaisenaan sillä hetkellä, kun sivusto viimeksi rakennettiin. Rivin voi linkittää suoraan: lisää osoitteen perään #r ja rivin numero.
vaitteet:
- id: p1
lainaus: "GEO: Generative Engine Optimization ... Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, Ameet Deshpande ... Submission history ... [v1] Thu, 16 Nov 2023 ... [v3] Fri, 28 Jun 2024 ... Comments: Accepted to KDD 2024"
url: https://arxiv.org/abs/2311.09735
lahde: "arXiv 2311.09735, abstraktisivu"
avattu: 2026-11-02
- id: p2
lainaus: "Through rigorous evaluation, we demonstrate that GEO can boost visibility by up to 40% in generative engine responses."
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: GEO (arXiv v3, HTML)"
avattu: 2026-11-02
- id: p3
lainaus: "we show the efficacy of these strategies varies across domains"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: GEO (arXiv v3, HTML)"
avattu: 2026-11-02
- id: p4
lainaus: "only the top 5 sources are fetched from the Google search engine for every query. ... The answer is then generated by the gpt3.5-turbo model"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: GEO, luku 3.1 (generatiivinen moottori)"
avattu: 2026-11-02
- id: p5
lainaus: "We sample 5 different responses at temperature=0.7, to reduce statistical deviations."
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: GEO, luku 3.1"
avattu: 2026-11-02
- id: p6
lainaus: "The setup closely mimics the workflow used in previous works and the general design adopted by commercial GEs."
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: GEO, luku 3.1"
avattu: 2026-11-02
- id: p7
lainaus: "Our benchmark comprises 10K queries divided into 8K, 1K, and 1K for train, validation, and test splits, respectively."
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: GEO-bench"
avattu: 2026-11-02
- id: p8
lainaus: "includes queries from nine different sources ... containing 80% informational queries and 10% each for transactional and navigational queries. ... GEO-bench consists of queries from 25 diverse domains such as Arts, Health, and Games."
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: GEO-bench"
avattu: 2026-11-02
- id: p9
lainaus: "Authoritative: Modifies text style of the source content to be more persuasive and authoritative. ... Keyword Stuffing: Modifies content to include more keywords from the query, as expected in classical SEO optimization. ... Statistics Addition ... Cite Sources ... Quotation Addition ... Easy-to-Understand ... Fluency Optimization ... Unique Words ... Technical Terms"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: yhdeksän GEO-menetelmää"
avattu: 2026-11-02
- id: p10
lainaus: "we randomly select one source website to be optimized"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: koeasetelma"
avattu: 2026-11-02
- id: p11
lainaus: "Position-Adjusted Word Count, which combines word count and position count ... reduces the weight by an exponentially decaying function of the citation position ... is the normalized word count of sentences related to a citation"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: mittarit"
avattu: 2026-11-02
- id: p12
lainaus: "a subjective metric encompassing seven different aspects ... Each sub-metric is evaluated using GPT-3.5, following a methodology akin to that described in G-Eval."
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: Subjective Impression -mittari"
avattu: 2026-11-02
- id: p13
lainaus: "our top-performing methods, Cite Sources, Quotation Addition, and Statistics Addition ... achieved a relative improvement of 30-40% on the Position-Adjusted Word Count metric ... 15-30% on the Subjective Impression metric"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: päätulokset"
avattu: 2026-11-02
- id: p14
lainaus: "Table 1 ... Position-Adjusted Word Count, Overall: No Optimization 19.3 ... Keyword Stuffing 17.7 ... Cite Sources 24.6 ... Quotation Addition 27.2 ... Statistics Addition 25.2"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: taulukko 1"
avattu: 2026-11-02
- id: p15
lainaus: "we find such methods offer little to no improvement on generative engine's responses"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: avainsanojen täyttö"
avattu: 2026-11-02
- id: p16
lainaus: "the Cite Sources method led to a substantial 115.1% increase in visibility for websites ranked fifth in SERP ... the visibility of the top-ranked website decreased by 30.3%"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: hakusijan vaikutus"
avattu: 2026-11-02
- id: p17
lainaus: "the best combination (Fluency Optimization and Statistics Addition) outperforming any single GEO strategy by more than 5.5%"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: yhdistelmät"
avattu: 2026-11-02
- id: p18
lainaus: "Authoritative significantly improves performance in debate-style questions ... question types like 'Opinion' benefit significantly from the addition of relevant statistics ... The method Quotation Addition is most effective in the 'People & Society,' 'Explanation,' and 'History' domains."
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: aluekohtaiset tulokset"
avattu: 2026-11-02
- id: p19
lainaus: "a commercially deployed generative engine ... provide source text as file uploads to perplexity.ai ... We evaluate all our methods on a subset of 200 samples of our test set."
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: Perplexity-koe (liite C.1)"
avattu: 2026-11-02
- id: p20
lainaus: "Quotation Addition performs best in Position-Adjusted Word Count with a 22% improvement over the baseline ... traditional SEO methods like Keyword Stuffing, are further highlighted, as it performs 10% worse than the baseline ... show improvements of up to 9% and 37% on the two metrics"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: Perplexity-tulokset"
avattu: 2026-11-02
- id: p21
lainaus: "methods may need to adapt over time as GEs evolve, mirroring the evolution of SEO ... owing to the black-box nature of search engine algorithms, we didn't evaluate how GEO methods affect search rankings ... the nature of queries can change over time, necessitating continuous updates ... future generative models will be able to ingest more sources ... there may be discrepancies due to subjective interpretations or errors in labeling"
url: https://arxiv.org/html/2311.09735v3
lahde: "Aggarwal ym.: rajoitukset"
avattu: 2026-11-02
- id: g1
lainaus: "you may see used to describe work specifically focused on improving visibility in AI search experiences ... optimizing for generative AI search is optimizing for the search experience, and thus still SEO."
url: https://developers.google.com/search/docs/fundamentals/ai-optimization-guide
lahde: "Google Search Central: Google's Guide to Optimizing for Generative AI Features (päivitetty 2026-07-10)"
avattu: 2026-11-02
- id: g2
lainaus: "You don't need to write in a specific way just for generative AI search. ... There's no requirement to break your content into tiny pieces for AI to better understand it. ... seeking inauthentic 'mentions' across the web isn't as helpful as it might seem. ... primarily to manipulate rankings or generative AI responses ... Last updated 2026-07-10 UTC."
url: https://developers.google.com/search/docs/fundamentals/ai-optimization-guide
lahde: "Google Search Central: Google's Guide to Optimizing for Generative AI Features"
avattu: 2026-11-02
- id: g3
lainaus: "There are no additional requirements to appear in AI Overviews or AI Mode, nor other special optimizations necessary. ... The best practices for SEO remain relevant for AI features in Google Search (such as AI Overviews and AI Mode). ... indexed and eligible to be shown in Google Search with a snippet"
url: https://developers.google.com/search/docs/appearance/ai-features
lahde: "Google Search Central: AI features and your website"
avattu: 2026-11-02
- id: s1
lainaus: "Optimizing Visibility in Generative Engines: A Critical Survey of Generative Engine Optimization ... Olivier Martinez ... July 15, 2026 ... it describes a relative visibility gain in a simulator in which five documents have already been placed in context."
url: https://arxiv.org/pdf/2607.14035
lahde: "Martinez: Critical Survey of GEO (arXiv 2607.14035, 2026)"
avattu: 2026-11-02
- id: s2
lainaus: "the source is already present in a five-document context, so Ds and much of Ks are fixed; ... with texts uploaded as files rather than web pages retrieved organically. ... no clicks, referrals, traffic, or purchases are observed;"
url: https://arxiv.org/pdf/2607.14035
lahde: "Martinez: Critical Survey of GEO, luku 4.3"
avattu: 2026-11-02
- id: s3
lainaus: "lies less in providing a recipe than in transforming a commercial intuition into an experimental problem. ... Subsequent work has, however, narrowed the scope of that conclusion:"
url: https://arxiv.org/pdf/2607.14035
lahde: "Martinez: Critical Survey of GEO"
avattu: 2026-11-02
- id: e1
lainaus: "We address this gap by introducing E-GEO, the first benchmark built specifically for e-commerce GEO. E-GEO contains over 7,000 realistic, multi-sentence consumer product queries paired with relevant listings"
url: https://arxiv.org/html/2511.20867v1
lahde: "Bagga ym.: E-GEO (arXiv 2511.20867)"
avattu: 2026-11-02
- id: e2
lainaus: "We use GPT-4o as the generative engine responsible for re-ranking. ... 10 of the 15 yield negligible or even negative changes in ranking."
url: https://arxiv.org/html/2511.20867v1
lahde: "Bagga ym.: E-GEO"
avattu: 2026-11-02
omat_luvut: []