Cover Image

Generalized Distributional Alignment Games for Unbiased Answer-Level Fine-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mohri, Mehryar, Schneider, Jon, Zhong, Yutao
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Distributional Alignment Games for Answer-Level Fine-Tuning
by: Mohri, Mehryar, et al.
Published: (2026)

Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning
by: Mohri, Mehryar, et al.
Published: (2026)

Mind the Gap: Structure-Aware Consistency in Preference Learning
by: Mohri, Mehryar, et al.
Published: (2026)

Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
by: Mohri, Mehryar, et al.
Published: (2026)

Beyond Tsybakov: Model Margin Noise and $\mathcal{H}$-Consistency Bounds
by: Mohri, Mehryar, et al.
Published: (2025)

Principled Algorithms for Optimizing Generalized Metrics in Binary Classification
by: Mao, Anqi, et al.
Published: (2025)

A Theoretical Framework for Modular Learning of Robust Generative Models
by: Cortes, Corinna, et al.
Published: (2026)

Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
by: Mao, Anqi, et al.
Published: (2024)

Regression with Multi-Expert Deferral
by: Mao, Anqi, et al.
Published: (2024)

$H$-Consistency Guarantees for Regression
by: Mao, Anqi, et al.
Published: (2024)

A Universal Growth Rate for Learning with Smooth Surrogate Losses
by: Mao, Anqi, et al.
Published: (2024)

Top-$k$ Classification and Cardinality-Aware Prediction
by: Mao, Anqi, et al.
Published: (2024)

Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer
by: Mao, Anqi, et al.
Published: (2025)

Improved Balanced Classification with Theoretically Grounded Loss Functions
by: Cortes, Corinna, et al.
Published: (2025)

Enhanced $H$-Consistency Bounds
by: Mao, Anqi, et al.
Published: (2024)

Principled Approaches for Learning to Defer with Multiple Experts
by: Mao, Anqi, et al.
Published: (2023)

Multi-Label Learning with Stronger Consistency Guarantees
by: Mao, Anqi, et al.
Published: (2024)

Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention
by: Mao, Anqi, et al.
Published: (2023)

Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms
by: Mao, Anqi, et al.
Published: (2023)

Budgeted Multiple-Expert Deferral
by: DeSalvo, Giulia, et al.
Published: (2025)

Coherence Mechanisms for Provable Self-Improvement
by: Mohri, Mehryar, et al.
Published: (2025)

Cardinality-Aware Set Prediction and Top-$k$ Classification
by: Cortes, Corinna, et al.
Published: (2024)

Optimized Deferral for Imbalanced Settings
by: Cortes, Corinna, et al.
Published: (2026)

Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data
by: Cortes, Corinna, et al.
Published: (2025)

Rational Transductors
by: Mohri, Mehryar
Published: (2026)

Algorithms for Learning Kernels Based on Centered Alignment
by: Cortes, Corinna, et al.
Published: (2012)

Rate-Preserving Reductions for Blackwell Approachability
by: Dann, Christoph, et al.
Published: (2024)

High-Dimensional Calibration from Swap Regret
by: Fishelson, Maxwell, et al.
Published: (2025)

Swap Regret and Correlated Equilibria Beyond Normal-Form Games
by: Arunachaleswaran, Eshwar Ram, et al.
Published: (2025)

Next-Token Prediction and Regret Minimization
by: Mohri, Mehryar, et al.
Published: (2026)

Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning
by: Dann, Christoph, et al.
Published: (2026)

Efficient Opportunistic Approachability
by: Marinov, Teodor Vanislavov, et al.
Published: (2026)

Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance
by: Block, Jacob L., et al.
Published: (2026)

Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization
by: Jiang, Ruichen, et al.
Published: (2026)

Differentially Private Domain Adaptation with Theoretical Guarantees
by: Bassily, Raef, et al.
Published: (2023)

Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment
by: Chen, Tiejin, et al.
Published: (2026)

Efficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned Diffusion Models
by: Zhang, Fengzhe, et al.
Published: (2025)

Fundamental Novel Consistency Theory: $H$-Consistency Bounds
by: Zhong, Yutao
Published: (2025)

Alignment Dynamics in LLM Fine-Tuning
by: Huang, Yuhan, et al.
Published: (2026)

GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
by: Gan, Wangjie, et al.
Published: (2026)