LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generation

TL;DR

This paper introduces LOT, a comprehensive Chinese long text benchmark with new datasets and a pretrained model LongLM, to evaluate and improve long text understanding and generation capabilities.

Contribution

The paper presents a new story-centric benchmark LOT and a large-scale Chinese long text pretrained model LongLM, addressing the lack of standardized evaluation for Chinese long text modeling.

Findings

LongLM outperforms similar-sized models on LOT tasks.

LOT effectively evaluates Chinese long text understanding and generation.

New datasets based on Chinese stories facilitate comprehensive assessment.

Abstract

Standard multi-task benchmarks are essential for developing pretraining models that can generalize to various downstream tasks. Existing benchmarks for natural language processing (NLP) usually focus only on understanding or generating short texts. However, long text modeling requires many distinct abilities in contrast to short texts, such as the modeling of long-range discourse and commonsense relations, and the coherence and controllability of generation. The lack of standardized benchmarks makes it difficult to assess these abilities of a model and fairly compare different models, especially Chinese models. Therefore, we propose a story-centric benchmark named LOT for evaluating Chinese long text modeling, which aggregates two understanding tasks and two generation tasks. We construct new datasets for these tasks based on human-written Chinese stories with hundreds of words. Furthermore, we release an encoder-decoder-based Chinese long text pretraining model named LongLM with up to 1 billion parameters. We pretrain LongLM on 120G Chinese novels with two generative tasks including text infilling and conditional continuation. Extensive experiments show that LongLM outperforms similar-sized pretraining models substantially on both the understanding and generation tasks in LOT.