# Claim Optimization in Computational Argumentation

arXiv: https://arxiv.org/abs/2212.08913 · HTML: https://mlsanity.com/paper/2212.08913/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 62 references that are in the map.
- First posted on arXiv 17 Dec 2022.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [WikiHow: A Large Scale Text Summarization Dataset](https://mlsanity.com/paper/1810.09305/) (2018)
- [Sequence-to-Sequence Learning as Beam-Search Optimization](https://mlsanity.com/paper/1606.02960/) (2016)
- [Automatically Neutralizing Subjective Bias in Text](https://mlsanity.com/paper/1911.09709/) (2019)
- [Understanding Iterative Revision from Human-Written Text](https://mlsanity.com/paper/2203.03802/) (2022)
- [Corpora Generation for Grammatical Error Correction](https://mlsanity.com/paper/1904.05780/) (2019)
- [Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models](https://mlsanity.com/paper/2205.11503/) (2022)
- [Aspect-Controlled Neural Argument Generation](https://mlsanity.com/paper/2005.00084/) (2020)
- [Learning To Split and Rephrase From Wikipedia Edit History](https://mlsanity.com/paper/1808.09468/) (2018)
- [Text Editing by Command](https://mlsanity.com/paper/2010.12826/) (2020)
- [Rhetoric, Logic, and Dialectic: Advancing Theory-based Argument Quality Assessment in Natural Language Processing](https://mlsanity.com/paper/2006.00843/) (2020)
- [Learning Household Task Knowledge from WikiHow Descriptions](https://mlsanity.com/paper/1909.06414/) (2019)
- [Belief-based Generation of Argumentative Claims](https://mlsanity.com/paper/2101.09765/) (2021)
- [Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale](https://mlsanity.com/paper/2101.10250/) (2021)
- [Annotation and Classification of Sentence-level Revision Improvement](https://mlsanity.com/paper/1909.05309/) (2019)
- [Assessing the Sufficiency of Arguments through Conclusion Generation](https://mlsanity.com/paper/2110.13495/) (2021)
- [ENTRUST: Argument Reframing with Language Models and Entailment](https://mlsanity.com/paper/2103.06758/) (2021)
- [Supporting Cognitive and Emotional Empathic Writing of Students](https://mlsanity.com/paper/2105.14815/) (2021)
- [Mining Naturally-occurring Corrections and Paraphrases from Wikipedia's Revision History](https://mlsanity.com/paper/2202.12575/) (2022)

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

- [To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support](https://mlsanity.com/paper/2305.16799/) (2023)
- [Argument Quality Assessment in the Age of Instruction-Following Large Language Models](https://mlsanity.com/paper/2403.16084/) (2024)
- [Abstract Weighted Based Gradual Semantics in Argumentation Theory](https://mlsanity.com/paper/2401.11472/) (2024)

## Abstract (arXiv)

An optimal delivery of arguments is key to persuasion in any debate, both for humans and for AI systems. This requires the use of clear and fluent claims relevant to the given debate. Prior work has studied the automatic assessment of argument quality extensively. Yet, no approach actually improves the quality so far. To fill this gap, this paper proposes the task of claim optimization: to rewrite argumentative claims in order to optimize their delivery. As multiple types of optimization are possible, we approach this task by first generating a diverse set of candidate claims using a large language model, such as BART, taking into account contextual information. Then, the best candidate is selected using various quality metrics. In automatic and human evaluation on an English-language corpus, our quality-based candidate selection outperforms several baselines, improving 60% of all claims (worsening 16% only). Follow-up analyses reveal that, beyond copy editing, our approach often specifies claims with details, whereas it adds less evidence than humans do. Moreover, its capabilities generalize well to other domains, such as instructional texts.