HiCaM: A Hierarchical-Causal Modification Framework for Long-Form Text Modification

TL;DR

HiCaM is a hierarchical-causal framework designed to improve long-form text modification by reducing irrelevant changes and ensuring coherence, demonstrating significant performance gains across multiple domains and models.

Contribution

We introduce HiCaM, a novel hierarchical-causal framework for long-form text modification, addressing key issues of irrelevance and coherence in existing LLM approaches.

Findings

Achieves up to 79.50% win rate over strong LLMs.

Demonstrates consistent improvements across multiple models and domains.

Provides a new multi-domain dataset for evaluation.

Abstract

Large Language Models (LLMs) have achieved remarkable success in various domains. However, when handling long-form text modification tasks, they still face two major problems: (1) producing undesired modifications by inappropriately altering or summarizing irrelevant content, and (2) missing necessary modifications to implicitly related passages that are crucial for maintaining document coherence. To address these issues, we propose HiCaM, a Hierarchical-Causal Modification framework that operates through a hierarchical summary tree and a causal graph. Furthermore, to evaluate HiCaM, we derive a multi-domain dataset from various benchmarks, providing a resource for assessing its effectiveness. Comprehensive evaluations on the dataset demonstrate significant improvements over strong LLMs, with our method achieving up to a 79.50\% win rate. These results highlight the comprehensiveness of our approach, showing consistent performance improvements across multiple models and domains.