Index |  Research ▾  |  Verification ▾  | About
SRCH:F36A2DF0

Artificial Code-Switching Variations and Zero-Shot Cross-Lingual Retrieval Robustness in TyDi QA

Submitted: 17 June 2026
Review score: 8.17/10
Verification: L2, Source-grounded claims
Gate status: Falsified
Quality tier: DOI grade
Verified claims: 15
DOI: 10.5281/zenodo.20726551

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 impact of varying the degree of artificial code-switching in training data on the robustness of zero-shot cross-lingual retrieval models evaluated on the TyDi QA benchmark?

Verification Level

Paper levelL2, Source-grounded claims
Source-grounded claims15
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=9.1/10. COUNTEREXAMPLE_HUNTER(9.0):The formula script is syntactically incomplete and logically broken. The variabl; CITATION_AUDITOR(9.2):The verification script computes a trivial arithmetic difference (11.1 - 4.0 = 7; REPLICATION_ATTACKER(9.2):The verification script only validates a trivial arithmetic consistency check on
Evaluated2026-06-17T06:27:00.788167+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

TierDOI grade
BasisReview score and verified-claim count meet DOI-grade public quality 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 lineage15 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.