HCOMP 2026 paper: error decomposition for human-in-the-loop evaluation of LLM data annotation
windx0303 · x · 2026-10-01
A paper to be presented at HCOMP 2026 / CI 2026, "Enhancing LLM-Based Data Annotation through Error Decomposition: A Human-in-the-Loop Evaluation Paradigm," proposes evaluating and improving LLM-based data annotation by decomposing errors within a human-in-the-loop framework.
More from Research
- AI Overviews cites 38% fewer self-promotional listicles, drops brands 83% of the time: data — lilyraynyc · 2026-10-01
- 98,877 historical newspaper pages (1700s-1940s) with OCR text and word boxes hit Hugging Face — vanstriendaniel · 2026-10-01
- Microsoft's new ML system forecasts power-grid damage from space weather 30-60 min ahead — LesterMackey · 2026-10-01
- Noam Brown on Dwarkesh Podcast: Agent Swarms, Alignment, and Recursive Self-Improvement — GregKamradt · 2026-10-01
- Keras 3's quiet ZeroModels project packs 100+ model families across JAX, PyTorch, TensorFlow — lmoroney · 2026-10-01
- Initial probing of Opus suggests its time estimates are hallucinated from human training samples — StefanoGogioso · 2026-10-01