Papers with Computational argumentation
Mining, Assessing, and Improving Arguments in NLP and the Social Sciences (2023.eacl-tutorials)
Copied to clipboard
| Challenge: | a tutorial on argument quality assessment will focus on what makes an argument good or bad . argument quality is a field encompassing varying tasks on the automated analysis and synthesis of natural language arguments. |
| Approach: | This tutorial will focus on the assessment of argument quality across disciplines . authors will involve participants in annotation studies on the quality assessment . |
| Outcome: | The tutorial will focus on the assessment of argument quality across disciplines . it will involve participants in two annotation studies on the quality assessment and the improvement of quality . |
Mining, Assessing, and Improving Arguments in NLP and the Social Sciences (2024.lrec-tutorials)
Copied to clipboard
| Challenge: | a tutorial on computational argumentation is updated to address the problem of argument quality . argument quality is a field of interdisciplinary research that connects natural language processing to social sciences . |
| Approach: | They present an updated version of the EACL 2023 tutorial on argument quality . they will focus on the notions of argument quality across disciplines . |
| Outcome: | The updated version of the EACL 2023 tutorial focuses on argument quality assessment . the authors will focus on the interface between Argument Mining and Deliberation Theory . |
Sentiment-Stance-Specificity (SSS) Dataset: Identifying Support-based Entailment among Opinions. (L18-1)
Copied to clipboard
| Challenge: | Argument mining is a method for extracting argument components and structures from natural language texts. |
| Approach: | They propose to model arguments as a set of premises that either support each other or collectively support a conclusion. |
| Outcome: | The proposed rules give an overall accuracy of 0.83 for the three datasets. |
Exploring the Potential of Large Language Models in Computational Argumentation (2024.acl-long)
Copied to clipboard
| Challenge: | Argumentation is an essential tool in various domains, including law, public policy, and artificial intelligence. |
| Approach: | They propose to evaluate LLMs on various computational argumentation tasks . they organize existing tasks into six main categories and standardize the format of 14 datasets . |
| Outcome: | The proposed model performs well on argument mining and argument generation tasks. |
CEDAR: A Chinese Evaluation Dataset for Computational Argumentation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing debate datasets neglect important labels for argument mining, generation, and evaluation. |
| Approach: | They propose a Chinese Evaluation Dataset for Computational Argumentation that includes key arguments and key rhetorical figures, debater roles, modal words, debate results and transcripts. |
| Outcome: | The proposed dataset covers 600 debates about 318 topics from Chinese debate competitions. |
ConQRet: A New Benchmark for Fine-Grained Automatic Evaluation of Retrieval Augmented Computational Argumentation (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for evaluating RAArg are costly and lack long, complex arguments and real-world evidence. |
| Approach: | They propose to use multiple fine-grained LLM judges to evaluate RAArg using a new benchmark that features long and complex human-authored arguments on debated topics. |
| Outcome: | The proposed methods provide better and more interpretable assessments than traditional single-score metrics and even previously reported human crowdsourcing. |