Skip to content
← Back to explorer

HFEPX Hub

CS.AI + Multilingual Papers

Updated from current HFEPX corpus (Mar 8, 2026). 13 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Mar 8, 2026). 13 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Pairwise. Frequent quality control: Gold Questions. Frequently cited benchmark: AdvBench. 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 27, 2026.

Papers: 13 Last published: Feb 27, 2026 Global RSS Tag RSS
Cs.AIMultilingual

Researcher Quick Triage

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

All Sampled Papers (13) Replication-Ready Only (3)

High-Signal Coverage

100.0%

13 / 13 sampled papers are not low-signal flagged.

Replication-Ready Set

3

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

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

Primary action: Start with the top 2 papers in “Start Here”, then validate assumptions in the protocol matrix.

Currently showing only replication-ready papers in ranking and matrix sections (3 papers).

Why This Matters For Eval Research

  • 76.9% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 46.2% of papers in this hub.
  • AdvBench is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Most common quality-control signal is gold-question checks (7.7% of papers).
  • Rater context is mostly domain experts, and annotation is commonly pairwise annotation; use this to scope replication staffing.
  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.

Benchmark Interpretation

  • AdvBench appears in 7.7% of hub papers (1/13); use this cohort for benchmark-matched comparisons.
  • ARC-Challenge appears in 7.7% of hub papers (1/13); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 30.8% of hub papers (4/13); compare with a secondary metric before ranking methods.
  • conciseness is reported in 15.4% of hub papers (2/13); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (76.9% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (15.4% vs 30% target).

  • Moderate: Papers naming benchmarks/datasets

    Coverage is usable but incomplete (30.8% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (53.8% vs 35% target).

  • Moderate: Papers with known rater population

    Coverage is usable but incomplete (23.1% vs 35% target).

  • Moderate: Papers with known annotation unit

    Coverage is usable but incomplete (23.1% vs 35% target).

Strengths

  • Strong human-feedback signal (76.9% of papers).
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.
  • Agentic evaluation appears in 30.8% of papers.

Known Gaps

  • Only 15.4% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (23.1% coverage).
  • Annotation unit is under-specified (23.1% coverage).

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (AdvBench vs ARC-Challenge) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and conciseness.
Recommended Queries (Expanded)

Recommended Queries

Judge vs Human Agreement Benchmark Slice: AdvBench Metric Slice: accuracy IAA-Reported Evaluations Recent High-Signal Papers

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
CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics

Dec 26, 2025

 Yes
Expert Verification
Automatic Metrics DROP , BIRD Accuracy Gold Questions
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking

Feb 27, 2026

 Yes
Red Team
Llm As Judge AdvBench , Jbf Eval Success rate , Jailbreak success rate Not Reported
The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective

Feb 15, 2026

 No
Not Reported
Automatic Metrics ARC Challenge Accuracy , Conciseness Not Reported

Protocol Diff (Top Papers)

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

Signal CricBench: A Multilingual Benchmark for Evaluating… Jailbreak Foundry: From Papers to Runnable Attacks… The Sufficiency-Conciseness Trade-off in LLM Self-E…
Human Feedback Expert VerificationRed TeamNot reported
Evaluation Modes Automatic MetricsLlm As JudgeAutomatic Metrics
Benchmarks DROP, BIRDAdvBench, Jbf EvalARC Challenge
Metrics AccuracySuccess rate, Jailbreak success rateAccuracy, Conciseness
Quality Controls Gold QuestionsNot reportedNot reported
Rater Population Domain ExpertsUnknownUnknown
Annotation Unit UnknownUnknownUnknown
Suggested Reading Order (Extended)

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

Suggested Reading Order

  1. EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training

    Start here for detailed protocol reporting and quality-control evidence. Signals: pairwise preferences. Abstract: We subsequently apply supervised fine-tuning, preference optimization, and chat vector merging to introduce robust instruction-following.

  2. Terminology Rarity Predicts Catastrophic Failure in LLM Translation of Low-Resource Ancient Languages: Evidence from Ancient Greek

    Start here for detailed protocol reporting and quality-control evidence. Signals: human evaluation. Focus: bleu. Abstract: This study presents the first systematic, reference-free human evaluation of large language model.

  3. Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking

    Start here for detailed protocol reporting and quality-control evidence. Signals: LLM-as-judge + red-team protocols. Focus: AdvBench / success rate. Abstract: This system enables a standardized AdvBench evaluation of.

  4. CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: automatic metrics + expert verification. Focus: DROP / accuracy. Abstract: We evaluate six state-of-the-art models, including.

  5. MENLO: From Preferences to Proficiency -- Evaluating and Modeling Native-like Quality Across 47 Languages

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: agreement. Abstract: Using MENLO, we create a dataset.

  6. MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: accuracy. Abstract: We introduce MuRating, a scalable framework.

  7. HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models

    Adds evaluation protocol evidence with expert verification for broader protocol coverage within this hub. Signals: expert verification. Focus: Hssbench. Abstract: Multimodal Large Language Models (MLLMs) have demonstrated significant.

  8. Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search

    Adds automatic metrics with red-team protocols for broader protocol coverage within this hub. Signals: automatic metrics + red-team protocols. Focus: accuracy. Abstract: As Large Language Models (LLMs) are.

Known Limitations

Known Limitations

  • Only 15.4% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (23.1% 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 (4)
  • Red Team (3)
  • Expert Verification (2)
  • Critique Edit (1)

Evaluation Modes

  • Automatic Metrics (6)
  • Human Eval (1)
  • Llm As Judge (1)
  • Simulation Env (1)

Top Benchmarks

  • AdvBench (1)
  • ARC Challenge (1)
  • BIRD (1)
  • Cricbench (1)

Top Metrics

  • Accuracy (4)
  • Conciseness (2)
  • Agreement (1)
  • Bertscore (1)

Rater Population Mix

  • Domain Experts (3)

Quality Controls

  • Gold Questions (1)
  • Inter Annotator Agreement Reported (1)
Coverage diagnostics (sample-based): human-feedback 76.9% · benchmarks 30.8% · metrics 53.8% · quality controls 15.4%.

Top Papers

Related Hubs

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

Post a Job Get a Quote