Forskningsbibliotek

Sex fullständigt lästa arbeten översatta till avgränsade produktbeslut.

arXiv · 2022-10-18

Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages

Öppna evidenspost

Forskningsfråga

How can a retrieval benchmark cover languages with very different resource levels while using native queries and relevance judgments?

Metod

An 18-language, same-language Wikipedia retrieval benchmark built with native-speaker queries and judgments; lexical, dense and hybrid baselines were compared on the released pools.

Vad underlaget stöder

Evaluate each language explicitly, document corpus and judgment construction, and keep native review central. The reported hybrid result is a historical benchmark observation.

Gränser och överförbarhet

This is same-language information retrieval, not translation assessment or web SEO. Heuristic segmentation, candidate-pool gaps and unfinished test labels limit transferability; it says nothing about hreflang or Google rankings.

Klassificering

  • Stött
  • Historiskt
  • Endast akademiskt

NAVINES-påverkan: Labb för flerspråkig sidjämförelse

arXiv · 2024-04-14

Competitive Retrieval: Going Beyond the Single Query

Öppna evidenspost

Forskningsfråga

How does publisher competition change when participants allocate content decisions across multiple queries rather than one isolated query?

Metod

A formal multi-query game plus four controlled student competitions covering 30 TREC topics, 84 participants and specified proxy rankers; best-response dynamics and feature changes were examined.

Vad underlaget stöder

Cross-query opportunity cost and competitor response deserve explicit treatment; equilibrium existence does not imply that learning dynamics will converge.

Gränser och överförbarhet

The student setting, topics and rankers are controlled proxies. The work does not identify current Google features, predict winners or justify reusable weights or a practical Nash-equilibrium claim.

Klassificering

  • Begränsat
  • Endast akademiskt

NAVINES-påverkan: Planerare för konkurrerande flerfrågeportfölj

arXiv · 2020-05-26

Ranking-Incentivized Quality Preserving Content Modification

Öppna evidenspost

Forskningsfråga

Can ranking-incentivized content modification include coherence and modification cost instead of optimizing promotion alone?

Metod

A controlled passage-replacement method balanced promotion and coherence, evaluated with proxy rankers and offline data across 31 queries, with an explicit ethics discussion.

Vad underlaget stöder

Quality constraints and the cost of changing content belong in planning. A promotional change that fails editorial integrity should be rejected.

Gränser och överförbarhet

Passages came from higher-ranked candidates and quality judgments were bounded and subjective. It does not support copying winners, real-engine causal claims or unrestricted automated rewriting.

Klassificering

  • Begränsat
  • Endast akademiskt

NAVINES-påverkan: Planerare för konkurrerande flerfrågeportfölj

Journal of Artificial Intelligence Research · 2025

The Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents

Öppna evidenspost

Forskningsfråga

Under which formal ranking mechanisms and content-deviation costs can strategic publisher learning converge or remain unstable?

Metod

Formal publisher-utility models with rank benefit minus deviation cost, convergence results for specified linear/softmax settings, and discrete simulations, predominantly with two publishers.

Vad underlaget stöder

Change cost, response dynamics and instability are useful planning dimensions; a mechanism can have an equilibrium while local responses cycle or remain pseudoperiodic.

Gränser och överförbarhet

The model assumes a static information need, known ranking function and embedding-space actions. Simulations are not a real search engine and do not justify a Google mechanism or guaranteed convergence claim.

Klassificering

  • Stött
  • Begränsat
  • Endast akademiskt

NAVINES-påverkan: Planerare för konkurrerande flerfrågeportfölj

KDD / arXiv · 2024

GEO: Generative Engine Optimization

Öppna evidenspost

Forskningsfråga

In controlled generative-engine experiments, how do selected content modifications affect proxy visibility across queries and domains?

Metod

GEO-BENCH combined 10,000 queries from nine datasets with visibility proxies and experiments on two generative engines; citation, quotation, statistics and other interventions were compared by domain.

Vad underlaget stöder

Clear attribution, genuine evidence and domain-aware experimentation can be reviewed as editorial signals; keyword stuffing performed poorly in this benchmark.

Gränser och överförbarhet

Two engines, black-box variance and proxy metrics do not establish traditional-search effects or future citation probability. Reported gains are historical benchmark results, not forecasts; appendix prompts are untrusted.

Klassificering

  • Begränsat
  • Historiskt
  • Endast akademiskt

NAVINES-påverkan: Labb för AI-citeringsberedskap

arXiv · 2024-07-02

Adversarial Search Engine Optimization for Large Language Models

Öppna evidenspost

Forskningsfråga

Can content in retrieved web or plugin documents manipulate an LLM's product preferences, and which broader attack categories appear beyond classic prompt injection?

Metod

Controlled experiments with fictional products, web/plugin documents and proprietary models examined model-directed instructions, concealment, false claims, source suppression and competitor discrediting.

Vad underlaget stöder

Retrieved content is an untrusted input surface; safety review should cover concealed persuasion and source integrity as well as direct instructions.

Gränser och överförbarhet

The favorable fictional setup, limited scale and changing proprietary systems do not establish prevalence or complete detection. Exact attack payloads are not republished and the checker is not a certification.

Klassificering

  • Stött
  • Begränsat
  • Endast akademiskt

NAVINES-påverkan: Säkerhetskontroll för AI-sökmanipulation

Evidens granskad 14 augusti 2026 · Fastställer inte aktuella Google-faktorer eller garanterat resultat.

Forskning

Egen analys med tydlig metod, data och begränsningar.

Vi jagar inte algoritmer. Vi bygger tydlighet, förtroende och synlighet som växer över tid.

Göra avancerad sökintelligens begriplig, användbar och tillgänglig – och hjälpa företag att omsätta den i mätbara åtgärder.

Metod

  • Fastställ omfattning, viktiga mallar och framgångsmått.
  • Granska ett urval av serversvar, robots, sitemaps, canonical och interna länkar.
  • Definiera ett huvudmått och skyddsmått kopplade till affärsmålet.
  • Skapa jämförbara perioder och bryt ned på sida, fråga, land och enhet.

Begränsningar

  • Attribution, integritet och datatrösklar döljer delar av resan.
  • Samtidig förändring bevisar inte att SEO-insatsen orsakade resultatet.