Skip to content
← Back to explorer

HFEPX Hub

CS.IR + Coding Papers

Updated from current HFEPX corpus (Feb 27, 2026). 21 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Ranking. 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: 21 Last published: Feb 26, 2026 Global RSS Tag RSS
Cs.IRCoding

Research Narrative

Grounded narrative Model: deterministic-grounded Source: persisted

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 21 papers for CS.IR + Coding Papers. Dominant protocol signals include automatic metrics, human evaluation, with frequent benchmark focus on Retrieval, DROP and metric focus on accuracy, latency. 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 61.9% of hub papers (13/21); use this cohort for benchmark-matched comparisons.
  • DROP appears in 4.8% of hub papers (1/21); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 23.8% of hub papers (5/21); compare with a secondary metric before ranking methods.
  • latency is reported in 14.3% of hub papers (3/21); compare with a secondary metric before ranking methods.

Researcher Checklist

  • Close gap on Papers with explicit human feedback. Coverage is a replication risk (9.5% vs 45% target).
  • Close gap on Papers reporting quality controls. Coverage is a replication risk (0% vs 30% target).
  • Maintain strength on Papers naming benchmarks/datasets. Coverage is strong (71.4% vs 35% target).
  • Maintain strength on Papers naming evaluation metrics. Coverage is strong (61.9% vs 35% target).
  • Close gap on Papers with known rater population. Coverage is a replication risk (4.8% vs 35% target).
  • Close gap on Papers with known annotation unit. Coverage is a replication risk (9.5% vs 35% target).

Papers with explicit human feedback

Coverage is a replication risk (9.5% vs 45% target).

Papers reporting quality controls

Coverage is a replication risk (0% vs 30% target).

Papers naming benchmarks/datasets

Coverage is strong (71.4% vs 35% target).

Papers naming evaluation metrics

Coverage is strong (61.9% vs 35% target).

Papers with known rater population

Coverage is a replication risk (4.8% vs 35% target).

Papers with known annotation unit

Coverage is a replication risk (9.5% vs 35% target).

Suggested Reading Order

  1. 1. SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables

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

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

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

  3. 3. 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.

  4. 4. A Benchmark for Deep Information Synthesis

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

  5. 5. A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives

    Adds automatic metrics for broader coverage within this hub.

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

    Adds automatic metrics for broader coverage within this hub.

  7. 7. HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders

    Adds automatic metrics with pairwise preferences for broader coverage within this hub.

  8. 8. NanoKnow: How to Know What Your Language Model Knows

    Adds automatic metrics for broader coverage within this hub.

Known Limitations

  • Only 0% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (4.8% 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=20

1 papers use both Human Eval and Automatic Metrics.

Benchmark Brief

Retrieval

Coverage: 13 papers (61.9%)

13 papers (61.9%) mention Retrieval.

Examples: MoDora: Tree-Based Semi-Structured Document Analysis System , Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators , Multi-Vector Index Compression in Any Modality

Benchmark Brief

DROP

Coverage: 1 papers (4.8%)

1 papers (4.8%) mention DROP.

Examples: SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables

Benchmark Brief

Financebench

Coverage: 1 papers (4.8%)

1 papers (4.8%) mention Financebench.

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

Metric Brief

accuracy

Coverage: 5 papers (23.8%)

5 papers (23.8%) mention accuracy.

Examples: MoDora: Tree-Based Semi-Structured Document Analysis System , NanoKnow: How to Know What Your Language Model Knows , Index Light, Reason Deep: Deferred Visual Ingestion for Visual-Dense Document Question Answering

Metric Brief

latency

Coverage: 3 papers (14.3%)

3 papers (14.3%) mention latency.

Examples: Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators , HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders , Query as Anchor: Scenario-Adaptive User Representation via Large Language Model

Metric Brief

relevance

Coverage: 3 papers (14.3%)

3 papers (14.3%) mention relevance.

Examples: Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering , The Invisible Hand of AI Libraries Shaping Open Source Projects and Communities , 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: SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables , MoDora: Tree-Based Semi-Structured Document Analysis System , Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Most Recent

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

Papers: SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables , MoDora: Tree-Based Semi-Structured Document Analysis System , Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Best Protocol Detail

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

Papers: SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables , MoDora: Tree-Based Semi-Structured Document Analysis System , Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Top Papers

Related Hubs