# Controllable Multi-document Summarization: Coverage & Coherence Intuitive Policy with Large Language Model Based Rewards

arXiv: https://arxiv.org/abs/2310.03473 · HTML: https://mlsanity.com/paper/2310.03473/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 5 Oct 2023.

## Builds on (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Learning Deep Transformer Models for Machine Translation](https://mlsanity.com/paper/1906.01787/) (2019)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Fine-tune BERT for Extractive Summarization](https://mlsanity.com/paper/1903.10318/) (2019)
- [Retrieval-Augmented Generation for Code Summarization via Hybrid GNN](https://mlsanity.com/paper/2006.05405/) (2020)
- [A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal](https://mlsanity.com/paper/2005.10070/) (2020)
- [Leveraging Graph to Improve Abstractive Multi-Document Summarization](https://mlsanity.com/paper/2005.10043/) (2020)
- [Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering](https://mlsanity.com/paper/2304.12102/) (2023)
- [PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization](https://mlsanity.com/paper/2110.08499/) (2021)
- [Exploring Controllable Text Generation Techniques](https://mlsanity.com/paper/2005.01822/) (2020)
- [A Causal Lens for Controllable Text Generation](https://mlsanity.com/paper/2201.09119/) (2022)
- [Analyzing and Interpreting Neural Networks for NLP: A Report on the First BlackboxNLP Workshop](https://mlsanity.com/paper/1904.04063/) (2019)
- [A Cross-Domain Transferable Neural Coherence Model](https://mlsanity.com/paper/1905.11912/) (2019)
- [Abstractive Multi-Document Summarization via Phrase Selection and Merging](https://mlsanity.com/paper/1506.01597/) (2015)
- [DynE: Dynamic Ensemble Decoding for Multi-Document Summarization](https://mlsanity.com/paper/2006.08748/) (2020)
- [How "Multi" is Multi-Document Summarization?](https://mlsanity.com/paper/2210.12688/) (2022)

## Built on by (most cited first, 1 of 1)

- [MDCure: A Scalable Pipeline for Multi-Document Instruction-Following](https://mlsanity.com/paper/2410.23463/) (2024)

## Abstract (arXiv)

Memory-efficient large language models are good at refining text input for better readability. However, controllability is a matter of concern when it comes to text generation tasks with long inputs, such as multi-document summarization. In this work, we investigate for a generic controllable approach for multi-document summarization that leverages the capabilities of LLMs to refine the text. In particular, we train a controllable content extraction scheme to extract the text that will be refined by an LLM. The scheme is designed with a novel coverage and coherence intuitive policy, which is duly rewarded by a passively trained LLM. Our approach yields competitive results in the evaluation using ROUGE metrics and outperforms potential baselines in coherence, as per human evaluation.