Index |  Research ▾  |  Verification ▾  | About
SRCH:CAD169A5

Performance of Targeted Lexical Injection versus Fine-Tuning and Adapters in XTREME-R Cross-Lingual Retrieval

Submitted: 14 June 2026
Review score: 7.50/10
Verification: L2, Source-grounded claims
Gate status: Falsified
Quality tier: DOI grade
Verified claims: 9
DOI: 10.5281/zenodo.20691749

Abstract

Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their performance in low-resource languages (LRLs), such as Swahili, often lags due to data scarcity and underrepresentation in pre-training. A key challenge is achieving robust cross-lingual lexical alignment, crucial for tasks like translation and cross-lingual information retrieval. This paper introduces Targeted Lexical Injection (TLI), a novel and efficient fine-tuning approach. We first demonstrate that Lugha-Llama-8B-wura, a Swahili-centric LLM, exhibits strong, near-perfect lexical alignment for Swahili-English

Research Question

How does the performance of Targeted Lexical Injection (TLI) compare to full fine-tuning and adapter-based methods on the XTREME-R benchmark for cross-lingual retrieval in low-resource language pairs like Swahili-English?

Verification Level

Paper levelL2, Source-grounded claims
Source-grounded claims9
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=9.3/10. COUNTEREXAMPLE_HUNTER(9.0):The verification record confirms only that a hardcoded script outputs a specific; CITATION_AUDITOR(9.5):The verification script is a hardcoded tautology that prints a pre-defined JSON ; REPLICATION_ATTACKER(9.5):The verification script is a hardcoded stub that prints a pre-determined value (
Evaluated2026-06-14T18:01:03.589671+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 lineage9 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.