Skip to content
← Back to explorer

HFEPX Hub

Multilingual + Pairwise Preference (Last 120 Days)

Updated from current HFEPX corpus (Apr 12, 2026). 16 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 16 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Llm As Judge. Most common rater population: Domain Experts. Common annotation unit: Pairwise. Frequent quality control: Calibration. Common metric signal: accuracy. Use this page to compare protocol setup, judge behavior, and labeling design decisions before running new eval experiments. Newest paper in this set is from Apr 2, 2026.

Papers: 16 Last published: Apr 2, 2026 Global RSS Tag RSS
MultilingualPairwise PreferenceLast 120d

Researcher Quick Triage

This hub is best used for protocol triage and replication planning from abstract-level evidence. Quality band: Developing .

High-Signal Coverage

100.0%

16 / 16 sampled papers are not low-signal flagged.

Replication-Ready Set

0

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

  • 0 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 0 papers support judge-vs-human agreement analysis.
  • 1 papers report explicit quality controls (calibration/adjudication/IAA).

Primary action: Use this page for scouting only; collect additional papers before attempting replication-critical comparisons.

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 100% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 31.3% of papers in this hub.
  • long-horizon tasks appears in 12.5% of papers, indicating agentic evaluation demand.

Protocol Takeaways

  • Most common quality-control signal is rater calibration (6.3% of papers).
  • Rater context is mostly domain experts, and annotation is commonly pairwise annotation; use this to scope replication staffing.
  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.

Metric Interpretation

  • accuracy is reported in 12.5% of hub papers (2/16); compare with a secondary metric before ranking methods.
  • agreement is reported in 6.3% of hub papers (1/16); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (100% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (6.3% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (0% vs 35% target).

  • Moderate: Papers naming evaluation metrics

    Coverage is usable but incomplete (31.3% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (12.5% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (37.5% vs 35% target).

Strengths

  • Strong human-feedback signal (100% of papers).

Known Gaps

  • Only 6.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (12.5% coverage).
  • Benchmark coverage is thin (0% of papers mention benchmarks/datasets).

Suggested Next Analyses

  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.
  • Track metric sensitivity by reporting both accuracy and agreement.
  • Add inter-annotator agreement checks when reproducing these protocols.
Recommended Queries (Expanded)

Recommended Queries

Start with These 3

Use these when you need one protocol anchor, one benchmark anchor, and one recent comparison point before reading the wider hub.

Start Here (Best First 6)

Ranked for protocol completeness (human signal, benchmark + metric anchors, quality controls, and judge/human overlap).

Protocol Matrix (Top 12)

Use this to quickly compare protocol ingredients instead of scanning long prose.

Paper HF Signal Eval Modes Benchmarks Metrics QC
Blinded Radiologist and LLM-Based Evaluation of LLM-Generated Japanese Translations of Chest CT Reports: Comparative Study

Apr 2, 2026

Yes Llm As Judge , Automatic Metrics Not Reported Accuracy Not Reported
Semantic Alignment across Ancient Egyptian Language Stages via Normalization-Aware Multitask Learning

Mar 25, 2026

Yes Automatic Metrics Not Reported Accuracy Not Reported
Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR

Mar 6, 2026

Yes Not Reported Not Reported Not Reported Calibration
Tutoring Large Language Models to be Domain-adaptive, Precise, and Safe

Feb 14, 2026

Yes Not Reported Not Reported Precision Not Reported
Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages

Feb 14, 2026

Yes Automatic Metrics Not Reported Toxicity Not Reported
CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models

Jan 8, 2026

Yes Automatic Metrics Not Reported Relevance Not Reported
Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not

Apr 6, 2026

Yes Not Reported Not Reported Not Reported Not Reported
Cross-Preference Learning for Sentence-Level and Context-Aware Machine Translation

Mar 26, 2026

Yes Not Reported Not Reported Not Reported Not Reported
Multilingual KokoroChat: A Multi-LLM Ensemble Translation Method for Creating a Multilingual Counseling Dialogue Dataset

Mar 24, 2026

Yes Not Reported Not Reported Not Reported Not Reported
Rethinking Metrics for Lexical Semantic Change Detection

Feb 17, 2026

Yes Automatic Metrics Not Reported Not Reported Not Reported
Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment

Feb 18, 2026

Yes Not Reported Not Reported Not Reported Not Reported
A Parallel Cross-Lingual Benchmark for Multimodal Idiomaticity Understanding

Jan 13, 2026

Yes Not Reported Not Reported Not Reported Not Reported

Protocol Diff (Top Papers)

Fast side-by-side comparison for the highest-ranked papers in this hub.

Signal Blinded Radiologist and LLM-Based Evaluation of LLM… Semantic Alignment across Ancient Egyptian Language… Do Compact SSL Backbones Matter for Audio Deepfake…
Human Feedback Pairwise PreferencePairwise PreferencePairwise Preference
Evaluation Modes Llm As Judge, Automatic MetricsAutomatic MetricsNot reported
Benchmarks Not reportedNot reportedNot reported
Metrics AccuracyAccuracyNot reported
Quality Controls Not reportedNot reportedCalibration
Rater Population Domain ExpertsUnknownUnknown
Annotation Unit PairwisePairwisePairwise
Suggested Reading Order (Extended)

This section is intentionally expanded only when needed; use “Start Here” above for a faster pass.

Suggested Reading Order

  1. Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not

    Start here for detailed protocol reporting and quality-control evidence. Signals: pairwise preferences. Abstract: We then evaluate Turkish and multilingual LLMs in a parallel preference-based setup that compares matched.

  2. Blinded Radiologist and LLM-Based Evaluation of LLM-Generated Japanese Translations of Chest CT Reports: Comparative Study

    Start here for detailed protocol reporting and quality-control evidence. Signals: LLM-as-judge + pairwise preferences. Focus: accuracy. Abstract: Objective: To evaluate the educational suitability of LLM-generated Japanese translations of.

  3. Cross-Preference Learning for Sentence-Level and Context-Aware Machine Translation

    Start here for detailed protocol reporting and quality-control evidence. Signals: pairwise preferences. Abstract: In this paper, we propose Cross-Preference Learning (CPL), a preference-based training framework that explicitly captures.

  4. Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: pairwise preferences. Abstract: We present RAPTOR, Representation Aware Pairwise-gated Transformer for Out-of-domain Recognition a controlled study of.

  5. Tutoring Large Language Models to be Domain-adaptive, Precise, and Safe

    Adds evaluation protocol evidence with pairwise preferences for broader protocol coverage within this hub. Signals: pairwise preferences. Focus: precision. Abstract: The methodological trajectory moves from classical supervised adaptation.

  6. Semantic Alignment across Ancient Egyptian Language Stages via Normalization-Aware Multitask Learning

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: accuracy. Abstract: We evaluate alignment quality using pairwise.

  7. Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: toxicity. Abstract: In response, we outline a practical.

  8. CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: relevance. Abstract: Prior work has identified language-related neurons.

Known Limitations

Known Limitations

  • Only 6.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (12.5% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
Research Utility Snapshot (Detailed)

Research Utility Snapshot

Human Feedback Mix

  • Pairwise Preference (16)

Evaluation Modes

  • Automatic Metrics (5)
  • Llm As Judge (1)

Top Benchmarks

Top Metrics

  • Accuracy (2)
  • Agreement (1)
  • Precision (1)
  • Relevance (1)

Rater Population Mix

  • Domain Experts (2)

Quality Controls

  • Calibration (1)
Coverage diagnostics (sample-based): human-feedback 100.0% · benchmarks 0.0% · metrics 31.3% · quality controls 6.3%.

Top Papers

Related Hubs

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