HFEPX Archive Slice

HFEPX Weekly Archive: 2025-W19

Updated from current HFEPX corpus (Mar 10, 2026). 7 papers are grouped in this daily page.

Read Full Context

Updated from current HFEPX corpus (Mar 10, 2026). 7 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics. Most common rater population: Domain Experts. Common annotation unit: Freeform. Frequent quality control: Calibration. Frequently cited benchmark: Pubhealthbench. 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 May 9, 2025.

Papers: 7 Last published: May 9, 2025 Global RSS

Researcher Quick Triage

Use this archive page for time-slice monitoring (what changed in evaluation methods, metrics, and protocol quality this period). Quality band: Developing .

High-Signal Coverage

100.0%

7 / 7 papers are not low-signal flagged.

Benchmark Anchors

14.3%

Papers with benchmark/dataset mentions in extraction output.

Metric Anchors

42.9%

Papers with reported metric mentions in extraction output.

1 papers report explicit quality controls for this archive period.
Prioritize papers with both benchmark and metric anchors for reliable longitudinal comparisons.

Primary action: Use this slice as early signal only; benchmark/metric anchoring is limited for rigorous period-over-period claims.

Get this digest every Friday →

Why This Time Slice Matters

42.9% of papers report explicit human-feedback signals, led by pairwise preferences.
automatic metrics appears in 28.6% of papers in this hub.
Pubhealthbench is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways For This Period

Most common quality-control signal is rater calibration (14.3% of papers).
Rater context is mostly domain experts, and annotation is commonly Freeform; use this to scope replication staffing.
Track metric sensitivity by reporting both accuracy and win rate.

Start Here (Highest-Signal Papers In This Slice)

Ranked by protocol completeness and evidence density for faster period-over-period review.

Healthy LLMs? Benchmarking LLM Knowledge of UK Government Public Health Information
May 9, 2025 · Citations: 0 · Score: 5.0

Eval: Automatic Metrics · Metrics: Accuracy
Mastering Multi-Drone Volleyball through Hierarchical Co-Self-Play Reinforcement Learning
May 7, 2025 · Citations: 0 · Score: 4.5

Eval: Automatic Metrics · Metrics: Win rate
Scalable LLM Reasoning Acceleration with Low-rank Distillation
May 8, 2025 · Citations: 0 · Score: 2.5

Eval: Not reported · Metrics: Latency
Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications
May 9, 2025 · Citations: 0 · Score: 2.0

Eval: Not reported · Metrics: Not reported
ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
May 5, 2025 · Citations: 0 · Score: 2.0

Eval: Not reported · Metrics: Not reported
RM-R1: Reward Modeling as Reasoning
May 5, 2025 · Citations: 0 · Score: 2.0

Eval: Not reported · Metrics: Not reported

Protocol Matrix (Top 10)

Quickly compare method ingredients across this archive slice.

Paper	Eval Modes	Benchmarks	Metrics	Quality Controls
Healthy LLMs? Benchmarking LLM Knowledge of UK Government Public Health Information May 9, 2025	Automatic Metrics	Pubhealthbench	Accuracy	Not reported
Mastering Multi-Drone Volleyball through Hierarchical Co-Self-Play Reinforcement Learning May 7, 2025	Automatic Metrics	Not reported	Win rate	Not reported
Scalable LLM Reasoning Acceleration with Low-rank Distillation May 8, 2025	Not reported	Not reported	Latency	Not reported
Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications May 9, 2025	Not reported	Not reported	Not reported	Not reported
ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization May 5, 2025	Not reported	Not reported	Not reported	Calibration
RM-R1: Reward Modeling as Reasoning May 5, 2025	Not reported	Not reported	Not reported	Not reported
When Your Own Output Becomes Your Training Data: Noise-to-Meaning Loops and a Formal RSI Trigger May 5, 2025	Not reported	Not reported	Not reported	Not reported

Researcher Workflow (Detailed)

Checklist

Moderate: Papers with explicit human feedback

Coverage is usable but incomplete (42.9% vs 45% target).
Gap: Papers reporting quality controls

Coverage is a replication risk (14.3% vs 30% target).
Gap: Papers naming benchmarks/datasets

Coverage is a replication risk (14.3% vs 35% target).
Moderate: Papers naming evaluation metrics

Coverage is usable but incomplete (28.6% vs 35% target).
Moderate: Papers with known rater population

Coverage is usable but incomplete (28.6% vs 35% target).
Moderate: Papers with known annotation unit

Coverage is usable but incomplete (28.6% vs 35% target).

Strengths

Agentic evaluation appears in 28.6% of papers.

Known Gaps

Only 14.3% of papers report quality controls; prioritize calibration/adjudication evidence.
Benchmark coverage is thin (14.3% of papers mention benchmarks/datasets).

Suggested Next Analyses

Track metric sensitivity by reporting both accuracy and win rate.
Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

Benchmark Slice: Pubhealthbench Metric Slice: accuracy Recent High-Signal Papers

Known Limitations

Only 14.3% of papers report quality controls; prioritize calibration/adjudication evidence.
Benchmark coverage is thin (14.3% 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)

Evaluation Modes

Automatic Metrics (2)

Top Metrics

Accuracy (1)
Win rate (1)

Top Benchmarks

Pubhealthbench (1)

Quality Controls

Calibration (1)

Papers In This Archive Slice

Healthy LLMs? Benchmarking LLM Knowledge of UK Government Public Health Information
Joshua Harris, Fan Grayson, Felix Feldman, Timothy Laurence, Toby Nonnenmacher · May 9, 2025 · Citations: 0

Web Browsing

However, while there are a number of LLM benchmarks in the medical domain, currently little is known about LLM knowledge within the field of public health.
Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications
Zhanliang Wang, Da Wu, Quan Nguyen, Zhuoran Xu, Kai Wang · May 9, 2025 · Citations: 0

Pairwise Preference

To address this challenge, we introduce MINT (Multimodal Integrated kNowledge Transfer), a framework that aligns unimodal large decoder models with domain-specific decision patterns from multimodal biomedical data through preference…
Scalable LLM Reasoning Acceleration with Low-rank Distillation
Harry Dong, Bilge Acun, Beidi Chen, Yuejie Chi · May 8, 2025 · Citations: 0

Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
Mastering Multi-Drone Volleyball through Hierarchical Co-Self-Play Reinforcement Learning
Ruize Zhang, Sirui Xiang, Zelai Xu, Feng Gao, Shilong Ji · May 7, 2025 · Citations: 0

Demonstrations Long Horizon

The task is turn-based, multi-agent, and physically grounded, posing significant challenges due to its long-horizon dependencies, tight inter-agent coupling, and the underactuated dynamics of quadrotors.
ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization
Dmitriy Shopkhoev, Ammar Ali, Magauiya Zhussip, Valentin Malykh, Stamatios Lefkimmiatis · May 5, 2025 · Citations: 0

Applied to several large language models (LLMs), ReplaceMe achieves up to 25\% pruning while retaining approximately 90\% of the original model's performance on open benchmarks - without any training or healing steps, resulting in minimal…
When Your Own Output Becomes Your Training Data: Noise-to-Meaning Loops and a Formal RSI Trigger
Rintaro Ando · May 5, 2025 · Citations: 0
RM-R1: Reward Modeling as Reasoning
Xiusi Chen, Gaotang Li, Ziqi Wang, Bowen Jin, Cheng Qian · May 5, 2025 · Citations: 0

Pairwise PreferenceRubric Rating

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning.

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

Post a Job Get a Quote