Skip to content
← Back to explorer

HFEPX Hub

CS.IR + General Papers

Updated from current HFEPX corpus (Apr 12, 2026). 23 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 23 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: Adjudication. Frequently cited benchmark: Innoeval. 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 Mar 19, 2026.

Papers: 23 Last published: Mar 19, 2026 Global RSS Tag RSS
Cs.IRGeneral

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%

23 / 23 sampled papers are not low-signal flagged.

Replication-Ready Set

2

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

  • 2 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

  • 73.9% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 52.2% of papers in this hub.
  • Innoeval is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Most common quality-control signal is adjudication (4.3% 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

  • Innoeval appears in 4.3% of hub papers (1/23); use this cohort for benchmark-matched comparisons.
  • Scirepeval appears in 4.3% of hub papers (1/23); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 17.4% of hub papers (4/23); compare with a secondary metric before ranking methods.
  • cost is reported in 13% of hub papers (3/23); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (73.9% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (4.3% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (17.4% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (60.9% vs 35% target).

  • Moderate: Papers with known rater population

    Coverage is usable but incomplete (26.1% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (43.5% vs 35% target).

Strengths

  • Strong human-feedback signal (73.9% of papers).
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.
  • Agentic evaluation appears in 47.8% of papers.

Known Gaps

  • Only 4.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Benchmark coverage is thin (17.4% of papers mention benchmarks/datasets).
  • LLM-as-judge appears without enough inter-annotator agreement reporting.

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (Innoeval vs Scirepeval) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • 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
SODIUM: From Open Web Data to Queryable Databases

Mar 19, 2026

Yes Automatic Metrics Sodium Bench Accuracy Not Reported
Beyond Paper-to-Paper: Structured Profiling and Rubric Scoring for Paper-Reviewer Matching

Apr 7, 2026

Yes Automatic Metrics Scirepeval Recall Not Reported
Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE

Mar 31, 2026

Yes Automatic Metrics Not Reported Ndcg , Cost Not Reported
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning

Apr 2, 2026

Yes Automatic Metrics Not Reported Relevance Not Reported
OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework

Mar 25, 2026

Yes Automatic Metrics Not Reported Latency , Relevance Not Reported
Automatic In-Domain Exemplar Construction and LLM-Based Refinement of Multi-LLM Expansions for Query Expansion

Feb 9, 2026

Yes Not Reported TREC Not Reported Not Reported
InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem

Feb 16, 2026

No
Not Reported
Llm As Judge Innoeval Not Reported Adjudication
HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders

Feb 24, 2026

Yes Not Reported Not Reported Latency , Cost Not Reported
Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition

Apr 26, 2025

Yes Automatic Metrics Not Reported Hit@5 Not Reported
Role-Augmented Intent-Driven Generative Search Engine Optimization

Aug 15, 2025

Yes Automatic Metrics Not Reported Perplexity Not Reported
TaoSR1: The Thinking Model for E-commerce Relevance Search

Aug 17, 2025

Yes Human Eval Not Reported Relevance Not Reported
AgenticRec: End-to-End Tool-Integrated Policy Optimization for Ranking-Oriented Recommender Agents

Mar 23, 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 SODIUM: From Open Web Data to Queryable Databases Beyond Paper-to-Paper: Structured Profiling and Rub… Aligning Multimodal Sequential Recommendations via…
Human Feedback Expert VerificationRubric RatingPairwise Preference
Evaluation Modes Automatic MetricsAutomatic MetricsAutomatic Metrics
Benchmarks Sodium BenchScirepevalNot reported
Metrics AccuracyRecallNdcg, Cost
Quality Controls Not reportedNot reportedNot reported
Rater Population Domain ExpertsDomain ExpertsDomain Experts
Annotation Unit UnknownMulti Dim RubricPairwise
Suggested Reading Order (Extended)

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

Suggested Reading Order

  1. Beyond Paper-to-Paper: Structured Profiling and Rubric Scoring for Paper-Reviewer Matching

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + rubric ratings. Focus: Scirepeval / recall. Abstract: It first performs hybrid retrieval that combines semantic.

  2. Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + pairwise preferences. Focus: relevance. Abstract: To bridge this gap, we introduce ReRanking Preference Optimization (RRPO),.

  3. Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + pairwise preferences. Focus: ndcg. Abstract: Preference-based alignment objectives have been widely adopted, from RLHF-style pairwise.

  4. TaoSR1: The Thinking Model for E-commerce Relevance Search

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + pairwise preferences. Focus: relevance. Abstract: Our framework, TaoSR1, involves three stages: (1) Supervised Fine-Tuning.

  5. SODIUM: From Open Web Data to Queryable Databases

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: automatic metrics + expert verification. Focus: Sodium-Bench / accuracy. Abstract: During research, domain experts often ask analytical.

  6. InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge. Focus: Innoeval. Abstract: However, existing idea evaluation methods often suffer from narrow knowledge horizons, flattened.

  7. Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: hit@5. Abstract: These domains typically involve fixed content.

  8. Role-Augmented Intent-Driven Generative Search Engine Optimization

    Adds automatic metrics with rubric ratings for broader protocol coverage within this hub. Signals: automatic metrics + rubric ratings. Focus: perplexity. Abstract: To better evaluate the method under.

Known Limitations

Known Limitations

  • Only 4.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Benchmark coverage is thin (17.4% of papers mention benchmarks/datasets).
  • 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 (9)
  • Critique Edit (3)
  • Rubric Rating (3)
  • Expert Verification (2)

Evaluation Modes

  • Automatic Metrics (12)
  • Human Eval (2)
  • Llm As Judge (1)

Top Benchmarks

  • Innoeval (1)
  • Scirepeval (1)
  • Sodium Bench (1)
  • TREC (1)

Top Metrics

  • Accuracy (4)
  • Cost (3)
  • Latency (3)
  • Relevance (3)

Rater Population Mix

  • Domain Experts (6)

Quality Controls

  • Adjudication (1)
Coverage diagnostics (sample-based): human-feedback 73.9% · benchmarks 17.4% · metrics 60.9% · quality controls 4.3%.

Top Papers

Related Hubs

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.