TIM: A Large-Scale Dataset and large Timeline Intelligence Model for Open-domain Timeline Summarization

TL;DR

This paper introduces TIM, a large-scale dataset and a novel timeline intelligence model designed for open-domain timeline summarization, effectively capturing topic evolution and filtering irrelevant information.

Contribution

The paper presents the first large-scale TLS dataset and a new TIM model with a progressive optimization strategy, including instruction tuning and dual-alignment reward learning.

Findings

TIM outperforms existing methods in open-domain timeline summarization.

The dataset contains over 1,000 news topics and 3,000 annotated instances.

The model effectively captures topic evolution and filters irrelevant details.

Abstract

Open-domain Timeline Summarization (TLS) is crucial for monitoring the evolution of news topics. To identify changes in news topics, existing methods typically employ general Large Language Models (LLMs) to summarize relevant timestamps from retrieved news. While general LLMs demonstrate capabilities in zero-shot news summarization and timestamp localization, they struggle with assessing topic relevance and understanding topic evolution. Consequently, the summarized information often includes irrelevant details or inaccurate timestamps. To address these issues, we propose the first large Timeline Intelligence Model (TIM) for open-domain TLS, which is capable of effectively summarizing open-domain timelines. Specifically, we begin by presenting a large-scale TLS dataset, comprising over 1,000 news topics and more than 3,000 annotated TLS instances. Furthermore, we propose a progressive optimization strategy, which gradually enhance summarization performance. It employs instruction tuning to enhance summarization and topic-irrelevant information filtering capabilities. Following this, it exploits a novel dual-alignment reward learning method that incorporates both semantic and temporal perspectives, thereby improving the understanding of topic evolution principles. Through this progressive optimization strategy, TIM demonstrates a robust ability to summarize open-domain timelines. Extensive experiments in open-domain demonstrate the effectiveness of our TIM.