# BatGPT: A Bidirectional Autoregessive Talker from Generative Pre-trained Transformer

Source: [BatGPT: A Bidirectional Autoregessive Talker from Generative Pre-trained Transformer](<https://www.sota2.com/research/paper/68fa705b1e209131cea4a8a0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:00.679Z

Authors: Zuchao Li, Shitou Zhang, Hai Zhao, Yifei Yang, Dongjie Yang

Published: 2023-07-01T15:10:01.000Z

## Abstract

BatGPT is a large-scale language model designed and trained jointly by Wuhan University and Shanghai Jiao Tong University. It is capable of generating highly natural and fluent text in response to various types of input, including text prompts, images, and audio. In the modeling level, we employ a bidirectional autoregressive architecture that allows the model to efficiently capture the complex dependencies of natural language, making it highly effective in tasks such as language generation, dialog systems, and question answering. Moreover, the bidirectional autoregressive modeling not only operates from left to right but also from right to left, effectively reducing fixed memory effects and alleviating model hallucinations.   In the training aspect, we propose a novel parameter expansion method for leveraging the pre-training of smaller models and employ reinforcement learning from both AI and human feedback, aimed at improving the model's alignment performance. Overall, these approaches significantly improve the effectiveness of BatGPT, and the model can be utilized for a wide range of natural language applications.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.00360>)

[PDF](<https://arxiv.org/pdf/2307.00360.pdf>)
