# Paper Abstract Writing through Editing Mechanism

arXiv: https://arxiv.org/abs/1805.06064 · HTML: https://mlsanity.com/paper/1805.06064/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2018.

## Built on by (most cited first, 9 of 9)

- [AMERICANO: Argument Generation with Discourse-driven Decomposition and Agent Interaction](https://mlsanity.com/paper/2310.20352/) (2023)
- [Large Language Models Penetration in Scholarly Writing and Peer Review](https://mlsanity.com/paper/2502.11193/) (2025)
- [MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective](https://mlsanity.com/paper/2210.14650/) (2022)
- [Can pre-trained language models generate titles for research papers?](https://mlsanity.com/paper/2409.14602/) (2024)
- [SuMe: A Dataset Towards Summarizing Biomedical Mechanisms](https://mlsanity.com/paper/2205.04652/) (2022)
- [Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging](https://mlsanity.com/paper/2507.05282/) (2025)
- [Non-Autoregressive Sentence Ordering](https://mlsanity.com/paper/2310.12640/) (2023)
- [DSAI: Unbiased and Interpretable Latent Feature Extraction for Data-Centric AI](https://mlsanity.com/paper/2412.06303/) (2024)
- [Automatic Generation of Titles for Research Papers Using Language Models](https://mlsanity.com/paper/2606.05085/) (2026)

## Abstract (arXiv)

We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract. We design a novel Writing-editing Network that can attend to both the title and the previously generated abstract drafts and then iteratively revise and polish the abstract. With two series of Turing tests, where the human judges are asked to distinguish the system-generated abstracts from human-written ones, our system passes Turing tests by junior domain experts at a rate up to 30% and by non-expert at a rate up to 80%.