CLDec 17, 2022

Claim Optimization in Computational Argumentation

arXiv:2212.08913v2196 citationsh-index: 36
Originality Incremental advance
AI Analysis

This addresses the need for AI systems to generate more persuasive arguments, though it is incremental as it builds on prior work in argument quality assessment.

The paper tackles the problem of improving argumentative claims by proposing claim optimization, which rewrites claims to enhance their delivery, and demonstrates that their quality-based selection method improves 60% of claims while worsening only 16% in evaluations.

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.

Code Implementations1 repo
Foundations

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

Your Notes