Skip to content
← Back to explorer

HFEPX Hub

Automatic Metrics + Multilingual Papers

Updated from current HFEPX corpus (Feb 27, 2026). 90 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Ranking. Frequent quality control: Gold Questions. Frequently cited benchmark: Retrieval. 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 Feb 26, 2026.

Papers: 90 Last published: Feb 26, 2026 Global RSS Tag RSS
Automatic MetricsMultilingual

Research Narrative

Grounded narrative Model: deterministic-grounded Source: persisted

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 90 papers for Automatic Metrics + Multilingual Papers. Dominant protocol signals include automatic metrics, simulation environments, human evaluation, with frequent benchmark focus on Retrieval, DROP and metric focus on accuracy, cost. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.

Why This Matters For Eval Research

Protocol Takeaways

Benchmark Interpretation

  • Retrieval appears in 10% of hub papers (9/90); use this cohort for benchmark-matched comparisons.
  • DROP appears in 3.3% of hub papers (3/90); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 23.3% of hub papers (21/90); compare with a secondary metric before ranking methods.
  • cost is reported in 6.7% of hub papers (6/90); compare with a secondary metric before ranking methods.

Researcher Checklist

  • Close gap on Papers with explicit human feedback. Coverage is a replication risk (13.3% vs 45% target).
  • Close gap on Papers reporting quality controls. Coverage is a replication risk (1.1% vs 30% target).
  • Tighten coverage on Papers naming benchmarks/datasets. Coverage is usable but incomplete (22.2% vs 35% target).
  • Tighten coverage on Papers naming evaluation metrics. Coverage is usable but incomplete (33.3% vs 35% target).
  • Close gap on Papers with known rater population. Coverage is a replication risk (11.1% vs 35% target).
  • Close gap on Papers with known annotation unit. Coverage is a replication risk (5.6% vs 35% target).

Papers with explicit human feedback

Coverage is a replication risk (13.3% vs 45% target).

Papers reporting quality controls

Coverage is a replication risk (1.1% vs 30% target).

Papers naming benchmarks/datasets

Coverage is usable but incomplete (22.2% vs 35% target).

Papers naming evaluation metrics

Coverage is usable but incomplete (33.3% vs 35% target).

Papers with known rater population

Coverage is a replication risk (11.1% vs 35% target).

Papers with known annotation unit

Coverage is a replication risk (5.6% vs 35% target).

Suggested Reading Order

  1. 1. Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning

    Start here for detailed protocol reporting, including rater and quality-control evidence.

  2. 2. Effective QA-driven Annotation of Predicate-Argument Relations Across Languages

    Start here for detailed protocol reporting, including rater and quality-control evidence.

  3. 3. Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks

    Start here for detailed protocol reporting, including rater and quality-control evidence.

  4. 4. Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads

    Adds automatic metrics for broader coverage within this hub.

  5. 5. SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African Context

    Adds automatic metrics for broader coverage within this hub.

  6. 6. Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

    Adds automatic metrics for broader coverage within this hub.

  7. 7. IndicIFEval: A Benchmark for Verifiable Instruction-Following Evaluation in 14 Indic Languages

    Adds automatic metrics for broader coverage within this hub.

  8. 8. MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models

    Adds automatic metrics with expert verification for broader coverage within this hub.

Known Limitations

  • Only 1.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (11.1% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.

Research Utility Links

human_eval vs automatic_metrics

both=1, left_only=0, right_only=89

1 papers use both Human Eval and Automatic Metrics.

automatic_metrics vs simulation_env

both=2, left_only=88, right_only=0

2 papers use both Automatic Metrics and Simulation Env.

simulation_env vs human_eval

both=0, left_only=2, right_only=1

0 papers use both Simulation Env and Human Eval.

Benchmark Brief

Retrieval

Coverage: 9 papers (10%)

9 papers (10%) mention Retrieval.

Examples: Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads , Structured Prompt Language: Declarative Context Management for LLMs , Cross-lingual Matryoshka Representation Learning across Speech and Text

Benchmark Brief

DROP

Coverage: 3 papers (3.3%)

3 papers (3.3%) mention DROP.

Examples: Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads , Mitigating Structural Noise in Low-Resource S2TT: An Optimized Cascaded Nepali-English Pipeline with Punctuation Restoration , CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics

Benchmark Brief

MMLU

Coverage: 3 papers (3.3%)

3 papers (3.3%) mention MMLU.

Examples: Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads , Indic-TunedLens: Interpreting Multilingual Models in Indian Languages , Enhancing Multilingual LLM Pretraining with Model-Based Data Selection

Metric Brief

accuracy

Coverage: 21 papers (23.3%)

21 papers (23.3%) mention accuracy.

Examples: MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models , Small Wins Big: Comparing Large Language Models and Domain Fine-Tuned Models for Sarcasm Detection in Code-Mixed Hinglish Text , Multilingual Large Language Models do not comprehend all natural languages to equal degrees

Metric Brief

cost

Coverage: 6 papers (6.7%)

6 papers (6.7%) mention cost.

Examples: Both Ends Count! Just How Good are LLM Agents at "Text-to-Big SQL"? , Small Language Models for Privacy-Preserving Clinical Information Extraction in Low-Resource Languages , Structured Prompt Language: Declarative Context Management for LLMs

Metric Brief

precision

Coverage: 4 papers (4.4%)

4 papers (4.4%) mention precision.

Examples: Small Language Models for Privacy-Preserving Clinical Information Extraction in Low-Resource Languages , Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning , Evaluating Extremely Low-Resource Machine Translation: A Comparative Study of ChrF++ and BLEU Metrics

Most Cited In This Hub

Fast path to methods with the strongest citation traction in this scope.

Papers: Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning , Effective QA-driven Annotation of Predicate-Argument Relations Across Languages , Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks

Most Recent

Fast path to latest protocol changes and newly published evaluation setups.

Papers: Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning , Effective QA-driven Annotation of Predicate-Argument Relations Across Languages , Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks

Best Protocol Detail

Papers with explicit rater/unit metadata and quality-control signals for reproducibility.

Papers: Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning , Effective QA-driven Annotation of Predicate-Argument Relations Across Languages , Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks

Top Papers

Related Hubs