A Tale of Two Error Categories: Exploring Concealed Trade-Offs in the Errors of Automated Judges in Evaluation of Uncertainty Quantifiers
cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
Comments: Accepted at INLG 2026
Code: https://github.com/evgeniael/auroc_eval
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Evaluation of Text Generation: A Survey
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Teaching Language Models to Faithfully Express their Uncertainty
- The Llama 3 Herd of Models
- Qwen2.5-Coder Technical Report
- Language Models (Mostly) Know What They Know
- OpenAI GPT-5 System Card
- Are LLM Decisions Faithful to Verbal Confidence?
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems