·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI1h◆SSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval1h◆Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence1h◆DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents1h◆MASkills: Continual Skills Optimization for Multi-Agent LLM Systems1h◆Competitive Market Behavior of LLMs1h◆Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model1h◆Training nGPT1h◆SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts1h◆Elite political incivility is rising across democracies1h◆Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation1h◆Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control1h◆FlashKAN: B-Spline KANs via Truncated Power Form1h◆Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL1h◆Similarity-Aware Personalized Federated Learning in Heterogeneous Environments1h◆Oracle, will I ever learn? A study of prediction convergence and complementarity across link prediction models1h◆UE5M3 FP4 Block Scaling for Stable Language Model Pretraining1h◆Network-Aware Forecasting on Wireless Access Points1h◆Monotonic anomaly detection1h◆Cantelli Constrained Policy Optimization1h◆Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI1h◆SSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval1h◆Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence1h◆DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents1h◆MASkills: Continual Skills Optimization for Multi-Agent LLM Systems1h◆Competitive Market Behavior of LLMs1h◆Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model1h◆Training nGPT1h◆SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts1h◆Elite political incivility is rising across democracies1h◆Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation1h◆Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control1h◆FlashKAN: B-Spline KANs via Truncated Power Form1h◆Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL1h◆Similarity-Aware Personalized Federated Learning in Heterogeneous Environments1h◆Oracle, will I ever learn? A study of prediction convergence and complementarity across link prediction models1h◆UE5M3 FP4 Block Scaling for Stable Language Model Pretraining1h◆Network-Aware Forecasting on Wireless Access Points1h◆Monotonic anomaly detection1h◆Cantelli Constrained Policy Optimization1h◆
News/Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation
arxiv
PublishedSeptember 1, 2026 at 4:00 AM

Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2608.26638v2 Announce Type: replace Abstract: Across various non-verifiable tasks, human evaluation is reliable but expensive, while automatic metrics are more scalable but often biased. Building on prediction-powered inference (PPI), we propose prediction-powered evaluation, a framework that

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivMeta-ethics and AI: exploring the novel meta-ethical questions in the era of AI1harxivSSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval1harxivEpistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence1harxivDocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents1h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews