Xiusi Chen

G<scp>otta</scp>: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation

2023 · Society for Industrial and Applied Mathematics eBooks

Few-shot question answering (QA) aims at precisely discovering answers to a set of questions from context passages while only a few training samples are available. Although existing studies have made some progress and can usually …

Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

2024 · arXiv (Cornell University)

Traditional reinforcement learning and planning typically requires vast amounts of data and training to develop effective policies. In contrast, large language models (LLMs) exhibit strong generalization and zero-shot capabilities, but struggle with tasks that require …

Self-Updatable Large Language Models by Integrating Context into Model Parameters

2024 · arXiv (Cornell University)

Despite significant advancements in large language models (LLMs), the rapid and frequent integration of small-scale experiences, such as interactions with surrounding objects, remains a substantial challenge. Two critical factors in assimilating these experiences are (1) …

ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation

2017 · arXiv (Cornell University)

A user can be represented as what he/she does along the history. A common way to deal with the user modeling problem is to manually extract all kinds of aggregated features over the heterogeneous behaviors, …

ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

A user can be represented as what he/she does along the history. A common way to deal with the user modeling problem is to manually extract all kinds of aggregated features over the heterogeneous behaviors, …