# 5W1H Extraction With Large Language Models

arXiv: https://arxiv.org/abs/2405.16150 · HTML: https://mlsanity.com/paper/2405.16150/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 25 May 2024.

## Builds on (most cited first, 18 of 18)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness](https://mlsanity.com/paper/2304.11633/) (2023)
- [Exploring the Feasibility of ChatGPT for Event Extraction](https://mlsanity.com/paper/2303.03836/) (2023)
- [Improving Translation Faithfulness of Large Language Models via Augmenting Instructions](https://mlsanity.com/paper/2308.12674/) (2023)
- [Giveme5W1H: A Universal System for Extracting Main Events from News Articles](https://mlsanity.com/paper/1909.02766/) (2019)
- [Reader-Aware Multi-Document Summarization: An Enhanced Model and The First Dataset](https://mlsanity.com/paper/1708.01065/) (2017)
- [MAILEX: Email Event and Argument Extraction](https://mlsanity.com/paper/2305.13469/) (2023)
- [Reader-Aware Multi-Document Summarization via Sparse Coding](https://mlsanity.com/paper/1504.07324/) (2015)

## Built on by (most cited first, 3 of 3)

- [Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation](https://mlsanity.com/paper/2602.01756/) (2026)
- [Explainable XR: Understanding User Behaviors of XR Environments using LLM-assisted Analytics Framework](https://mlsanity.com/paper/2501.13778/) (2025)
- [Reasoning-Guided Claim Normalization for Noisy Multilingual Social Media Posts](https://mlsanity.com/paper/2511.05078/) (2025)

## Abstract (arXiv)

The extraction of essential news elements through the 5W1H framework (textitWhat, textitWhen, textitWhere, textitWhy, textitWho, and textitHow) is critical for event extraction and text summarization. The advent of Large language models (LLMs) such as ChatGPT presents an opportunity to address language-related tasks through simple prompts without fine-tuning models with much time. While ChatGPT has encountered challenges in processing longer news texts and analyzing specific attributes in context, especially answering questions about textitWhat, textitWhy, and textitHow. The effectiveness of extraction tasks is notably dependent on high-quality human-annotated datasets. However, the absence of such datasets for the 5W1H extraction increases the difficulty of fine-tuning strategies based on open-source LLMs. To address these limitations, first, we annotate a high-quality 5W1H dataset based on four typical news corpora (textitCNN/DailyMail, textitXSum, textitNYT, textitRA-MDS); second, we design several strategies from zero-shot/few-shot prompting to efficient fine-tuning to conduct 5W1H aspects extraction from the original news documents. The experimental results demonstrate that the performance of the fine-tuned models on our labelled dataset is superior to the performance of ChatGPT. Furthermore, we also explore the domain adaptation capability by testing the source-domain (e.g. NYT) models on the target domain corpus (e.g. CNN/DailyMail) for the task of 5W1H extraction.