Skip to content
← Back to explorer

Benchmark Hub

Retrieval In CS.IR Papers

Updated from current HFEPX corpus (Feb 27, 2026). 31 papers are grouped in this benchmark page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Ranking. Frequent quality control: Calibration. 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: 31 Last published: Feb 26, 2026 Global RSS

Research Narrative

Grounded narrative Model: deterministic-grounded Source: persisted

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 31 papers for Retrieval In CS.IR Papers. Dominant protocol signals include automatic metrics, human evaluation, simulation environments, with frequent benchmark focus on Retrieval, BrowseComp and metric focus on accuracy, recall. 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 100% of hub papers (31/31); use this cohort for benchmark-matched comparisons.
  • BrowseComp appears in 3.2% of hub papers (1/31); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 19.4% of hub papers (6/31); compare with a secondary metric before ranking methods.
  • recall is reported in 16.1% of hub papers (5/31); compare with a secondary metric before ranking methods.

Researcher Checklist

  • Close gap on Papers with explicit human feedback. Coverage is a replication risk (9.7% vs 45% target).
  • Close gap on Papers reporting quality controls. Coverage is a replication risk (3.2% vs 30% target).
  • Maintain strength on Papers naming benchmarks/datasets. Coverage is strong (100% vs 35% target).
  • Maintain strength on Papers naming evaluation metrics. Coverage is strong (45.2% vs 35% target).
  • Close gap on Papers with known rater population. Coverage is a replication risk (6.5% vs 35% target).
  • Tighten coverage on Papers with known annotation unit. Coverage is usable but incomplete (22.6% vs 35% target).

Papers with explicit human feedback

Coverage is a replication risk (9.7% vs 45% target).

Papers reporting quality controls

Coverage is a replication risk (3.2% vs 30% target).

Papers naming benchmarks/datasets

Coverage is strong (100% vs 35% target).

Papers naming evaluation metrics

Coverage is strong (45.2% vs 35% target).

Papers with known rater population

Coverage is a replication risk (6.5% vs 35% target).

Papers with known annotation unit

Coverage is usable but incomplete (22.6% vs 35% target).

Suggested Reading Order

  1. 1. MoDora: Tree-Based Semi-Structured Document Analysis System

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

  2. 2. Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

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

  3. 3. Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training

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

  4. 4. A Benchmark for Deep Information Synthesis

    Include a human-eval paper to anchor calibration against automated judge settings.

  5. 5. Retrieval Challenges in Low-Resource Public Service Information: A Case Study on Food Pantry Access

    Adds simulation environments for broader coverage within this hub.

  6. 6. Revisiting RAG Retrievers: An Information Theoretic Benchmark

    Adds automatic metrics for broader coverage within this hub.

  7. 7. Revisiting Text Ranking in Deep Research

    Adds automatic metrics for broader coverage within this hub.

  8. 8. Multi-Vector Index Compression in Any Modality

    Adds automatic metrics for broader coverage within this hub.

Known Limitations

  • Only 3.2% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (6.5% 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=29

1 papers use both Human Eval and Automatic Metrics.

automatic_metrics vs simulation_env

both=0, left_only=30, right_only=1

0 papers use both Automatic Metrics and Simulation Env.

human_eval vs simulation_env

both=0, left_only=1, right_only=1

0 papers use both Human Eval and Simulation Env.

Benchmark Brief

Retrieval

Coverage: 31 papers (100%)

31 papers (100%) mention Retrieval.

Examples: MoDora: Tree-Based Semi-Structured Document Analysis System , Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators , Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training

Benchmark Brief

BrowseComp

Coverage: 1 papers (3.2%)

1 papers (3.2%) mention BrowseComp.

Examples: Revisiting Text Ranking in Deep Research

Benchmark Brief

Financebench

Coverage: 1 papers (3.2%)

1 papers (3.2%) mention Financebench.

Examples: Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering

Metric Brief

accuracy

Coverage: 6 papers (19.4%)

6 papers (19.4%) mention accuracy.

Examples: MoDora: Tree-Based Semi-Structured Document Analysis System , Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training , Index Light, Reason Deep: Deferred Visual Ingestion for Visual-Dense Document Question Answering

Metric Brief

recall

Coverage: 5 papers (16.1%)

5 papers (16.1%) mention recall.

Examples: E-MMKGR: A Unified Multimodal Knowledge Graph Framework for E-commerce Applications , RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering , Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering

Metric Brief

relevance

Coverage: 3 papers (9.7%)

3 papers (9.7%) mention relevance.

Examples: KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration , Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering , OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models

Most Cited In This Hub

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

Papers: MoDora: Tree-Based Semi-Structured Document Analysis System , Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators , Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training

Most Recent

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

Papers: MoDora: Tree-Based Semi-Structured Document Analysis System , Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators , Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training

Best Protocol Detail

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

Papers: MoDora: Tree-Based Semi-Structured Document Analysis System , Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators , Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training

Top Papers On This Benchmark

Other Benchmark Hubs

Retrieval Benchmark Papers With Accuracy (32) Retrieval In CS.CL Papers (104) Retrieval Benchmark Papers (115) Retrieval + Automatic Metrics Benchmark Papers (106) Retrieval In CS.AI Papers (58) Retrieval + General Benchmark Papers (62) Retrieval Benchmark Papers (Last 365 Days) (111) Retrieval Benchmark Papers (Last 180 Days) (92) Retrieval Benchmark Papers (Last 240 Days) (95) Retrieval Benchmark Papers (Last 300 Days) (104) Retrieval Benchmark Papers (Last 30 Days) (70) Retrieval Benchmark Papers (Last 150 Days) (89) Retrieval Benchmark Papers (Last 120 Days) (83) Retrieval Benchmark Papers (Last 90 Days) (78) Retrieval Benchmark Papers (Last 45 Days) (72) Retrieval Benchmark Papers (Last 60 Days) (77) Retrieval Benchmark Papers (Last 75 Days) (77) Retrieval + Coding Benchmark Papers (36) MATH + Math Benchmark Papers (20) MATH Benchmark Papers (20) MMLU Benchmark Papers (16) MMLU In CS.CL Papers (16) MATH In CS.CL Papers (17) MMLU + Automatic Metrics Benchmark Papers (16)