Cover Image

Limitations of refinement methods for weak to strong generalization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Somerstep, Seamus, Ritov, Ya'acov, Yurochkin, Mikhail, Maity, Subha, Sun, Yuekai
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A transfer learning framework for weak-to-strong generalization
by: Somerstep, Seamus, et al.
Published: (2024)

Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairness
by: Somerstep, Seamus, et al.
Published: (2024)

Learning In Reverse Causal Strategic Environments With Ramifications on Two Sided Markets
by: Somerstep, Seamus, et al.
Published: (2024)

Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
by: Polo, Felipe Maia, et al.
Published: (2024)

From Thomas Bayes to Big Data: On the feasibility of being a subjective Bayesian
by: Ritov, Ya'acov
Published: (2025)

No need for an oracle: the nonparametric maximum likelihood decision in the compound decision problem is minimax
by: Ritov, Ya'acov
Published: (2023)

A mixture of a normal distribution with random mean and variance -- Examples of inconsistency of maximum likelihood estimates
by: Ritov, Ya'acov
Published: (2024)

Microfoundation Inference for Strategic Prediction
by: Bracale, Daniele, et al.
Published: (2024)

Weak Supervision Performance Evaluation via Partial Identification
by: Polo, Felipe Maia, et al.
Published: (2023)

Learning to Choose or Choosing to Learn: Best-of-N vs. Supervised Fine-Tuning for Bit String Generation
by: Somerstep, Seamus, et al.
Published: (2025)

Aligners: Decoupling LLMs and Alignment
by: Ngweta, Lilian, et al.
Published: (2024)

CARROT: A Cost Aware Rate Optimal Router
by: Somerstep, Seamus, et al.
Published: (2025)

Learning the Distribution Map in Reverse Causal Performative Prediction
by: Bracale, Daniele, et al.
Published: (2024)

A Latent Variable Framework for Scaling Laws in Large Language Models
by: Cai, Peiyao, et al.
Published: (2025)

The Root Finding Problem Revisited: Beyond the Robbins-Monro procedure
by: Yu, Yue, et al.
Published: (2025)

Prompt Exploration with Prompt Regression
by: Feffer, Michael, et al.
Published: (2024)

Limits of definable families and dilations in nilmanifolds
by: Peterzil, Ya'acov, et al.
Published: (2024)

Estimation and Inference for the Average Treatment Effect in a Score-Explained Heterogeneous Treatment Effect Model
by: Wibisono, Kevin Christian, et al.
Published: (2025)

Fusing Models with Complementary Expertise
by: Wang, Hongyi, et al.
Published: (2023)

Bridging Human and LLM Judgments: Understanding and Narrowing the Gap
by: Polo, Felipe Maia, et al.
Published: (2025)

tinyBenchmarks: evaluating LLMs with fewer examples
by: Polo, Felipe Maia, et al.
Published: (2024)

Diagnosis-based mortality prediction for intensive care unit patients via transfer learning
by: Xu, Mengqi, et al.
Published: (2025)

Robust inference for risk heterogeneity under group imbalance
by: Xu, Mengqi, et al.
Published: (2026)

Distributionally Robust Performative Prediction
by: Xue, Songkai, et al.
Published: (2024)

The infinitesimal subgroup of interpretable groups in some dp-minimal valued fields
by: Halevi, Yatir, et al.
Published: (2025)

Semisimple groups interpretable in various valued fields
by: Halevi, Yatir, et al.
Published: (2023)

On groups interpretable in various valued fields
by: Halevi, Yatir, et al.
Published: (2022)

Efficient multi-prompt evaluation of LLMs
by: Polo, Felipe Maia, et al.
Published: (2024)

Out-of-Distribution Detection using Synthetic Data Generation
by: Abbas, Momin, et al.
Published: (2025)

Likelihood-Free Estimation for Spatiotemporal Hawkes processes with missing data and application to predictive policing
by: Das, Pramit, et al.
Published: (2025)

Uncertainty Quantification via Stable Distribution Propagation
by: Petersen, Felix, et al.
Published: (2024)

Maximin Relative Improvement: Fair Learning as a Bargaining Problem
by: Han, Jiwoo, et al.
Published: (2026)

On scalable oversight with weak LLMs judging strong LLMs
by: Kenton, Zachary, et al.
Published: (2024)

Automated Feature Labeling with Token-Space Gradient Descent
by: Schulz, Julian, et al.
Published: (2025)

CharED: Character-wise Ensemble Decoding for Large Language Models
by: Gu, Kevin, et al.
Published: (2024)

Dynamic Pricing in the Linear Valuation Model using Shape Constraints
by: Bracale, Daniele, et al.
Published: (2025)

Revenue Maximization Under Sequential Price Competition Via The Estimation Of s-Concave Demand Functions
by: Bracale, Daniele, et al.
Published: (2025)

Distributional Preference Alignment of LLMs via Optimal Transport
by: Melnyk, Igor, et al.
Published: (2024)

Estimation with missing not at random binary outcomes via exponential tilts
by: Maity, Subha
Published: (2025)

Adversarially-Robust TD Learning with Markovian Data: Finite-Time Rates and Fundamental Limits
by: Maity, Sreejeet, et al.
Published: (2025)