Related papers: General learned delegation by clones

Sampling is a promising bottom-up method for exposing what generative models have learned about language, but it remains unclear how to generate representative samples from popular masked language models (MLMs) like BERT. The MLM objective…

This article firstly attempts to explore parallel algorithms of learning distributed representations for both entities and relations in large-scale knowledge repositories with {\it MapReduce} programming model on a multi-core processor. We…

Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generation, the next token's probability distribution is derived from…

In Federated Learning, model training is performed across multiple computing devices, where only parameters are shared with a common central server without exchanging their data instances. This strategy assumes abundance of resources on…

Centralized learning requires data to be aggregated at a central server, which poses significant challenges in terms of data privacy and bandwidth consumption. Federated learning presents a compelling alternative, however, vanilla federated…

Modern AI agents such as large language models are trained on diverse tasks -- translation, code generation, mathematical reasoning, and text prediction -- simultaneously. A key question is how to quantify the influence of each individual…

Machine learning algorithms in socially sensitive domains (e.g., credit decisions) often focus on equalizing predictive outcomes. However, satisfying these metrics does not guarantee that models use the same reasoning for different groups.…

Despite strong performance in many sequence-to-sequence tasks, autoregressive models trained with maximum likelihood estimation suffer from exposure bias, i.e. the discrepancy between the ground-truth prefixes used during training and the…

Measuring the similarity between two different sentential arguments is an important task in argument mining. However, one of the challenges in this field is that the dataset must be annotated using expertise in a variety of topics, making…

Model merging aims to integrate multiple expert models into a single model that inherits their complementary strengths without incurring the inference-time cost of ensembling. Recent progress has shown that merging can be highly effective…

Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Training (PST), a label-free fine-tuning framework in which multiple language models improve…

We propose a parametric family of algorithms for personalized federated learning with locally convex user costs. The proposed framework is based on a generalization of convex clustering in which the differences between different users'…

A widely used paradigm to improve the generalization performance of high-capacity neural models is through the addition of auxiliary unsupervised tasks during supervised training. Tasks such as similarity matching and input reconstruction…

A major challenge for reinforcement learning is automatically generating curricula to reduce training time or improve performance in some target task. We introduce SEBNs (Skill-Environment Bayesian Networks) which model a probabilistic…

Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together…

Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory…

One-Shot Federated Learning (FL) is a recent paradigm that enables multiple clients to cooperatively learn a global model in a single round of communication with a central server. In this paper, we analyze the One-Shot FL problem through…

Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-intensive optimization. Online prompt selection presents a plausible solution by prioritizing…

Language models have become effective at a wide range of tasks, from math problem solving to open-domain question answering. However, they still make mistakes, and these mistakes are often repeated across related queries. Natural language…

Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e.g., can be up to 2048X in large-scale ensemble tasks. However, we found that the majority of computations in ensemble…