Key-Element-Informed sLLM Tuning for Document Summarization

2024/06/07 by Sangwon Ryu, Ryu, Sangwon, Heejin Do +7 · 3 citations
Computer Science · #Advanced Text Analysis Techniques #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2406.04625

openalex publication_date 2024/06/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Remarkable advances in large language models (LLMs) have enabled high-quality text summarization. However, this capability is currently accessible only through LLMs of substantial size or proprietary LLMs with usage fees. In response, smaller-scale LLMs (sLLMs) of easy accessibility and low costs have been extensively studied, yet they often suffer from missing key information and entities, i.e., low relevance, in particular, when input documents are long. We hence propose a key-element-informed instruction tuning for summarization, so-called KEITSum, which identifies key elements in documents and instructs sLLM to generate summaries capturing these key elements. Experimental results on dialogue and news datasets demonstrate that sLLM with KEITSum indeed provides high-quality summarization with higher relevance and less hallucinations, competitive to proprietary LLM.

Cited by

• Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
• Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrection
• Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents

Related

• Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method
• Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency
• A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches
• Summarization is (Almost) Dead
• Scaling Up Summarization: Leveraging Large Language Models for Long Text Extractive Summarization