Lipo: Listwise preference optimization through learning-to-rank
Aligning language models (LMs) with curated human feedback is critical to control their
behaviors in real-world applications. Several recent policy optimization methods, such as …
behaviors in real-world applications. Several recent policy optimization methods, such as …
Calibration-compatible Listwise Distillation of Privileged Features for CTR Prediction
In machine learning systems, privileged features refer to the features that are available
during offline training but inaccessible for online serving. Previous studies have recognized …
during offline training but inaccessible for online serving. Previous studies have recognized …
Understanding the Ranking Loss for Recommendation with Sparse User Feedback
Z Lin, J Pan, S Zhang, X Wang, X Xiao, S Huang… - arXiv preprint arXiv …, 2024 - arxiv.org
Click-through rate (CTR) prediction holds significant importance in the realm of online
advertising. While many existing approaches treat it as a binary classification problem and …
advertising. While many existing approaches treat it as a binary classification problem and …
Explain then Rank: Scale Calibration of Neural Rankers Using Natural Language Explanations from Large Language Models
The process of scale calibration in ranking systems involves adjusting the outputs of rankers
to correspond with significant qualities like click-through rates or relevance, crucial for …
to correspond with significant qualities like click-through rates or relevance, crucial for …
A Self-boosted Framework for Calibrated Ranking
Scale-calibrated ranking systems are ubiquitous in real-world applications nowadays, which
pursue accurate ranking quality and calibrated probabilistic predictions simultaneously. For …
pursue accurate ranking quality and calibrated probabilistic predictions simultaneously. For …
TF4CTR: Twin Focus Framework for CTR Prediction via Adaptive Sample Differentiation
Effective feature interaction modeling is critical for enhancing the accuracy of click-through
rate (CTR) prediction in industrial recommender systems. Most of the current deep CTR …
rate (CTR) prediction in industrial recommender systems. Most of the current deep CTR …
Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing
The powerful generative abilities of large language models (LLMs) show potential in
generating relevance labels for search applications. Previous work has found that directly …
generating relevance labels for search applications. Previous work has found that directly …
Personalized Transformer-based Ranking for e-Commerce at Yandex
K Khrylchenko, A Fritzler - arXiv preprint arXiv:2310.03481, 2023 - arxiv.org
Personalizing the user experience with high-quality recommendations based on user
activities is vital for e-commerce platforms. This is particularly important in scenarios where …
activities is vital for e-commerce platforms. This is particularly important in scenarios where …
[PDF][PDF] Beyond Binary Preference: Leveraging Bayesian Approaches for Joint Optimization of Ranking and Calibration
Predicting click-through rate (CTR) is a critical task in recommendation systems, where the
models are optimized with pointwise loss to infer the probability of items being clicked. In …
models are optimized with pointwise loss to infer the probability of items being clicked. In …
[PDF][PDF] A Brief Tutorial on Supervised Learning to Rank
P Hager, M de Rijke - 2023 - philipphager.github.io
A Brief Tutorial on Supervised Learning to Rank Page 1 A Brief Tutorial on Supervised
Learning to Rank Philipp Hager, Maarten de Rijke May 15, 2023 University of Amsterdam pkhager@uva.nl …
Learning to Rank Philipp Hager, Maarten de Rijke May 15, 2023 University of Amsterdam pkhager@uva.nl …