HERA: Improving Long Document Summarization using Large Language Models with Context Packaging and Reordering

📅 2025-02-01
📈 Citations: 0
Influential: 0
📄 PDF

career value

188K/year
🤖 AI Summary
Large language models (LLMs) struggle with long-document summarization due to event information dispersion and disrupted narrative logic, leading to inaccurate comprehension. To address this, we propose HERA—a novel framework introducing *context packing and reordering*. First, the input document is segmented based on semantic structure; second, cross-segment retrieval identifies fragments pertaining to the same event, which are then reordered into a logically coherent context; finally, the reordered context is fed into a zero-shot LLM for summary generation. HERA requires no fine-tuning, external training, or additional computational resources. Crucially, it enhances the model’s ability to capture event-level causal and temporal dependencies. Evaluated on two major long-document summarization benchmarks, HERA consistently outperforms strong baselines across ROUGE, BERTScore, and faithfulness metrics—demonstrating significant and robust improvements in both informativeness and factual consistency.

Technology Category

Application Category

📝 Abstract
Despite the rapid growth of context length of large language models (LLMs) , LLMs still perform poorly in long document summarization. An important reason for this is that relevant information about an event is scattered throughout long documents, and the messy narrative order impairs the accurate understanding and utilization of LLMs for long documents. To address these issues, we propose a novel summary generation framework, called HERA. Specifically, we first segment a long document by its semantic structure and retrieve text segments about the same event, and finally reorder them to form the input context. We evaluate our approach on two long document summarization datasets. The experimental results show that HERA outperforms foundation models in ROUGE, BERTScore and faithfulness metrics, while HERA does not require additional fine-tuning and resources.
Problem

Research questions and friction points this paper is trying to address.

Large Language Models
Summarization
Disorganized Information
Innovation

Methods, ideas, or system contributions that make the work stand out.

HERA method
enhanced understanding and performance
improved summarization quality
🔎 Similar Papers
No similar papers found.
T
Taiji Li
College of Computer Science and Technology, Zhejiang University
H
Hao Chen
Ant Group, China
F
Fei Yu
Ant Group, China
Y
Yin Zhang
College of Computer Science and Technology, Zhejiang University