Neural Information Processing Systems http://nips.cc/

Is it possible to adapt them in a similar way for use as general-purpose decoders?

We study how to use naturally available user feedback, such as clicks, to optimize large language model (LLM) pipelines for generating personalized sentences using prompts. Naive approaches, which estimate the policy gradient in the prompt space, suffer either from variance caused by the large action space of prompts or bias caused by inaccurate reward predictions. To circumvent these challenges, we propose a novel kernel-based off-policy gradient method, which estimates the policy gradient by leveraging similarity among generated sentences, substantially reducing variance while suppressing the bias. Empirical results on our newly established suite of benchmarks demonstrate the effectiveness of the proposed approach in generating personalized descriptions for movie recommendations, particularly when the number of candidate prompts is large.

Tabular data is considered the last unconquered castle of deep learning, yet the task of data stream classification is stated to be an equally important and demanding research area. Due to the temporal constraints, it is assumed that deep learning methods are not the optimal solution for application in this field. However, excluding the entire -- and prevalent -- group of methods seems rather rash given the progress that has been made in recent years in its development. For this reason, the following paper is the first to present an approach to natural language data stream classification using the sentence space method, which allows for encoding text into the form of a discrete digital signal. This allows the use of convolutional deep networks dedicated to image classification to solve the task of recognizing fake news based on text data. Based on the real-life Fakeddit dataset, the proposed approach was compared with state-of-the-art algorithms for data stream classification based on generalization ability and time complexity.

We propose a novel reinforcement learning based framework PoBRL for solving multi-document summarization. PoBRL jointly optimizes over the following three objectives necessary for a high-quality summary: importance, relevance, and length. Our strategy decouples this multi-objective optimization into different subproblems that can be solved individually by reinforcement learning. Utilizing PoBRL, we then blend each learned policies together to produce a summary that is a concise and complete representation of the original input. Our empirical analysis shows state-of-the-art performance on several multi-document datasets. Human evaluation also shows that our method produces high-quality output.