On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,738 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “Rank-Calibration”

Uncertainty in Language Models: Assessment through Rank-Calibrationcs.CL

New framework assesses LM uncertainty without thresholding.

problem Uncertainty quantification for LMs, especially comparing different measures.

method Rank-Calibration framework to assess uncertainty and confidence measures.

result Higher uncertainty correlates with lower generation quality.

Language Models Uncertainty Quantification Rank-Calibration Natural Language Generation Confidence Measures

2024-04-04abs ↗pdf ↗

The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Reviewstat.AP

Experiment shows author rankings can improve peer review scores.

problem Improving accuracy in machine learning conference peer review.

method Used Isotonic Mechanism to calibrate review scores using author rankings.

result Calibrated scores outperform raw scores in estimating ground truth review scores.

ICML 2023 author rankings peer review Isotonic Mechanism machine learning

2024-08-24abs ↗pdf ↗

Calibrated Preference Learning: The Case of Label Rankingcs.LG

The paper addresses calibration in label ranking, a structured prediction task.

problem Calibration in label ranking is not well understood and often poorly calibrated.

method Formalized calibration for label ranking, developed a hierarchy of notions, and empirically evaluated models.

result Popular label ranking models are often poorly calibrated, with differences between sub-ranking and top-k metrics.

calibration label ranking structured prediction pairwise prediction top-k prediction

2026-05-28abs ↗pdf ↗

Enforcing Calibration in Multi-Output Probabilistic Regression with Pre-rank Regularizationstat.ML

New method improves calibration in multi-output probabilistic models.

problem Challenges in achieving multivariate calibration in multi-output regression.

method General regularization framework to enforce multivariate calibration during training for arbitrary pre-rank functions.

result Significant improvement in calibration across all pre-rank functions without sacrificing predictive accuracy.

calibration multi-output regression probabilistic models pre-rank functions regularization

2025-10-24abs ↗pdf ↗

Enhancing Uplift Modeling in Multi-Treatment Marketing Campaigns: Leveraging Score Ranking and Calibration Techniquesstat.ML

This paper enhances uplift modeling for multi-treatment marketing campaigns.

problem Optimizing marketing strategies by selecting individuals likely to respond to different treatments.

method Leveraging score ranking and calibration techniques.

result Improves overall performance of marketing campaigns.

uplift modeling multi-treatment marketing score ranking calibration techniques marketing analytics

2024-08-24abs ↗pdf ↗