Related papers: Alice: Proactive Learning with Teacher's Demonstra…

Applied mathematics and machine computations have raised a lot of hope since the recent success of supervised learning. Many practitioners in industries have been trying to switch from their old paradigms to machine learning. Interestingly,…

Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on either reinforcement learning (RL) with verifiable signals or supervised…

The field of Weakly Supervised Learning (WSL) has recently seen a surge of popularity, with numerous papers addressing different types of "supervision deficiencies". In WSL use cases, a variety of situations exists where the collected…

The availability of labelled data is one of the main limitations in machine learning. We can alleviate this using weak supervision: a framework that uses expert-defined rules $\boldsymbol{\lambda}$ to estimate probabilistic labels…

Large Language Models (LLMs) require alignment with human preferences to avoid generating offensive, false, or meaningless content. Recently, low-resource methods for LLM alignment have been popular, while still facing challenges in…

Aligning powerful AI models on tasks that surpass human evaluation capabilities is the central problem of \textbf{superalignment}. To address this problem, weak-to-strong generalization aims to elicit the capabilities of strong models…

Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…

The weak-to-strong generalization phenomenon is the driver for important machine learning applications including highly data-efficient learning and, most recently, performing superalignment. While decades of research have resulted in…

Diffusion models generate synthetic images through an iterative refinement process. However, the misalignment between the simulation-free objective and the iterative process often causes accumulated gradient error along the sampling…

The goal of diffusion generative models is to align the learned distribution with the real data distribution through gradient score matching. However, inherent limitations in training data quality, modeling strategies, and architectural…

Weak-to-strong generalization refers to the phenomenon where a stronger model trained under supervision from a weaker one can outperform its teacher. While prior studies aim to explain this effect, most theoretical insights are limited to…

Active learning (AL) accelerates scientific discovery by prioritizing the most informative experiments, but traditional machine learning (ML) models used in AL suffer from cold-start limitations and domain-specific feature engineering,…

Training a supervised neural network classifier typically requires many annotated training samples. Collecting and annotating a large number of data points are costly and sometimes even infeasible. Traditional annotation process uses a…

Power-law scaling indicates that large-scale training with uniform sampling is prohibitively slow. Active learning methods aim to increase data efficiency by prioritizing learning on the most relevant examples. Despite their appeal, these…

We initiate a unified theoretical and algorithmic study of a key problem in weak-to-strong (W2S) generalization: when fine-tuning a strong pre-trained student with pseudolabels from a weaker teacher on a downstream task with spurious…

There is increasing interest in distilling task-specific knowledge from large language models (LLM) to smaller student models. Nonetheless, LLM distillation presents a dual challenge: 1) there is a high cost associated with querying the…

Story understanding and generation have long been a challenging task in natural language processing (NLP), especially when dealing with various levels of instruction specificity. In this paper, we propose a novel approach called "Weak to…

Self-supervised learning (SSL) has recently achieved promising performance for 3D medical image analysis tasks. Most current methods follow existing SSL paradigm originally designed for photographic or natural images, which cannot…

Ensuring robust safety measures across a wide range of scenarios is crucial for user-facing systems. While Large Language Models (LLMs) can generate valuable data for safety measures, they often exhibit distributional biases, focusing on…

We introduce Integrated Weak Learning, a principled framework that integrates weak supervision into the training process of machine learning models. Our approach jointly trains the end-model and a label model that aggregates multiple…