Index |  Research ▾  |  Verification ▾  | About
SRCH:E4B97BD1

Training Data Volume and Zero-Shot Cross-Lingual Retrieval Performance Gaps in WebFAQ 2.0

Submitted: 15 June 2026
Review score: 8.50/10
Verification: L2, Source-grounded claims
Gate status: Falsified
Quality tier: Flagship candidate
Verified claims: 16
DOI: 10.5281/zenodo.20696914

Abstract

Abstract: Transferring information retrieval (IR) models from a high-resource language (typically English) to other languages in a zero-shot fashion has become a widely adopted approach. In this work, we show that the effectiveness of zero-shot rankers diminishes when queries and documents are present in different languages. Motivated by this, we propose to train ranking models on artificially code-switched data instead, which we generate by utilizing bilingual lexicons. To this end, we experiment with lexicons induced from (1) cross-lingual word embeddings and (2) parallel Wikipedia page titles. We use

Research Question

What is the correlation between training data volume in WebFAQ 2.0 and zero-shot cross-lingual retrieval performance gaps across the 75 supported languages?

Verification Level

Paper levelL2, Source-grounded claims
Source-grounded claims16
Claim record sourceparsed source sections

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Truth-Engine Gate Verdict

StatusFalsified
GateGate 2 — Verification (formal proof or sandbox reproduction)
Reason[Gate 3 RED-TEAM FALSIFIED] avg_attack_score=6.8/10. COUNTEREXAMPLE_HUNTER(8.5):The formula reproduces a claimed gap of +4.0 MRR@10 for MoIR, but this is a sing; CITATION_AUDITOR(2.5):The formula script does not actually compute the performance gap but simply outp; REPLICATION_ATTACKER(9.5):The verification script is a tautology that hardcodes the claimed value (4.0) ra
Evaluated2026-06-15T18:11:32.875365+00:00

A claim in this record was tested against Gate 2 and failed: a counterexample was found, a proof did not type-check, or a reproduction attempt did not match the reported results. Evidence for the failure is attached to this record. VERIFIED requires an attached reproducible artifact (Lean4 proof source, or repro script and results) before this status can be set; it is not derived from review score or claim count.

Quality Tier

TierFlagship candidate
BasisReview score, verified-claim count, and public artifact coverage meet flagship-candidate thresholds.

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Evidence strength MEDIUM
Citation grounding MEDIUM
Uncertainty disclosure MEDIUM
Reproducibility status HIGH

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

StatusCURRENT
Correction count0
Manifest contractpaper-manifest-v1.1
Correction contractcorrection-record-v1

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance

PublisherAssignee Research
Public provenanceL4, External archival record
Report artifactAvailable
External recordRegistered
Claim lineage16 aggregate source-grounded claims
Review methodAutomated multi-reviewer assessment
Quality guideHow to read scores, claims, manifests, and evidence links
Provenance contractsource-provenance-v1
NoteMachine-generated synthesis of existing literature. Not primary research.