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

arXiv: https://arxiv.org/abs/2505.24319 · HTML: https://mlsanity.com/paper/2505.24319/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 22 of 22)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [QuALITY: Question Answering with Long Input Texts, Yes!](https://mlsanity.com/paper/2112.08608/) (2021)
- [LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs](https://mlsanity.com/paper/2408.07055/) (2024)
- [A Distributional Approach to Controlled Text Generation](https://mlsanity.com/paper/2012.11635/) (2020)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [Controlled Text Generation with Natural Language Instructions](https://mlsanity.com/paper/2304.14293/) (2023)
- [PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation](https://mlsanity.com/paper/2010.02301/) (2020)
- [Attribute Alignment: Controlling Text Generation from Pre-trained Language Models](https://mlsanity.com/paper/2103.11070/) (2021)
- [Parallel Refinements for Lexically Constrained Text Generation with BART](https://mlsanity.com/paper/2109.12487/) (2021)
- [Language Models can Self-Lengthen to Generate Long Texts](https://mlsanity.com/paper/2410.23933/) (2024)
- [Controlled Text Generation using T5 based Encoder-Decoder Soft Prompt Tuning and Analysis of the Utility of Generated Text in AI](https://mlsanity.com/paper/2212.02924/) (2022)
- [PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation](https://mlsanity.com/paper/2210.07431/) (2022)
- [Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking](https://mlsanity.com/paper/2307.14440/) (2023)
- [Harnessing the Plug-and-Play Controller by Prompting](https://mlsanity.com/paper/2402.04160/) (2024)

## Abstract (arXiv)

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.