A Typologically Grounded Evaluation Framework for Word Order and Morphology Sensitivity in Multilingual Masked LMs

Anna Feldman, Libby Barak, Jing Peng · Feb 28, 2026 · Citations: 0

Abstract

We introduce a typology-aware diagnostic for multilingual masked language models that tests reliance on word order versus inflectional form. Using Universal Dependencies, we apply inference-time perturbations: full token scrambling, content-word scrambling with function words fixed, dependency-based head--dependent swaps, and sentence-level lemma substitution (+L), which lemmatizes both the context and the masked target label. We evaluate mBERT and XLM-R on English, Chinese, German, Spanish, and Russian. Full scrambling drives word-level reconstruction accuracy near zero in all languages; partial and head--dependent perturbations cause smaller but still large drops. +L has little effect in Chinese but substantially lowers accuracy in German/Spanish/Russian, and it does not mitigate the impact of scrambling. Top-5 word accuracy shows the same pattern: under full scrambling, the gold word rarely appears among the five highest-ranked reconstructions. We release code, sampling scripts, and balanced evaluation subsets; Turkish results under strict reconstruction are reported in the appendix.

HFEPX Relevance Assessment

This paper appears adjacent to HFEPX scope (human-feedback/eval), but does not show strong direct protocol evidence in metadata/abstract.

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Ranking
Expertise required: Coding, Multilingual
Extraction source: Runtime deterministic fallback

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.35
Flags: low_signal, possible_false_positive, runtime_fallback_extraction

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

accuracy

Research Brief

Deterministic synthesis

We introduce a typology-aware diagnostic for multilingual masked language models that tests reliance on word order versus inflectional form. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 3, 2026, 7:09 AM · Grounded in abstract + metadata only

Key Takeaways

We introduce a typology-aware diagnostic for multilingual masked language models that tests reliance on word order versus inflectional form.
We evaluate mBERT and XLM-R on English, Chinese, German, Spanish, and Russian.
We release code, sampling scripts, and balanced evaluation subsets; Turkish results under strict reconstruction are reported in the appendix.

Researcher Actions

Treat this as method context, then pivot to protocol-specific HFEPX hubs.
Identify benchmark choices from full text before operationalizing conclusions.
Validate metric comparability (accuracy).

Caveats

Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
Low-signal flag detected: protocol relevance may be indirect.

Recommended Queries

human-eval protocol design pairwise preference data quality inter-rater agreement adjudication

Research Summary

Contribution Summary

We introduce a typology-aware diagnostic for multilingual masked language models that tests reliance on word order versus inflectional form.
We evaluate mBERT and XLM-R on English, Chinese, German, Spanish, and Russian.
We release code, sampling scripts, and balanced evaluation subsets; Turkish results under strict reconstruction are reported in the appendix.

Why It Matters For Eval

We release code, sampling scripts, and balanced evaluation subsets; Turkish results under strict reconstruction are reported in the appendix.

Researcher Checklist

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Pass: Evaluation mode is explicit

Detected: Automatic Metrics
Gap: Quality control reporting appears

No calibration/adjudication/IAA control explicitly detected.
Gap: Benchmark or dataset anchors are present

No benchmark/dataset anchor extracted from abstract.
Pass: Metric reporting is present

Detected: accuracy

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era Category Neighbor

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (accuracy, framework)
Confusion-Aware Rubric Optimization for LLM-based Automated Grading Category Neighbor

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (accuracy, framework)
IDP Accelerator: Agentic Document Intelligence from Extraction to Compliance Validation Category Neighbor

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (accuracy, framework)
Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance Category Neighbor

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (accuracy, framework)
Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning Category Neighbor

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (accuracy, framework)
DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science Category Neighbor

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (accuracy)
When Metrics Disagree: Automatic Similarity vs. LLM-as-a-Judge for Clinical Dialogue Evaluation Category Neighbor

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.CL)
- Shared metric mentions
- Shared terminology (accuracy)
A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (framework)

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote