CLOct 5, 2023

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

arXiv:2310.03473v11 citationsh-index: 7
AI Analysis

This work addresses controllability for users in multi-document summarization, but it is incremental as it builds on existing LLM-based methods with a novel policy.

The paper tackles the problem of controllability in multi-document summarization by proposing a generic approach that uses a controllable content extraction scheme with a coverage and coherence intuitive policy, rewarded by a passively trained LLM, resulting in competitive ROUGE scores and improved coherence in human evaluations.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes