Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation

December 21, 2023 · Entered Twilight · 🏛 Conference on Empirical Methods in Natural Language Processing

Repo contents: README.md, arg-llama, argtersely, data, experiments, filtering, finetune.py, get_argjudge_score.py, qsd_valid, requirements.txt, templates, utils

Authors Jiayu Lin, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei arXiv ID 2312.13608 Category cs.CL: Computation & Language Citations 18 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/amazingljy1206/ArgTersely ⭐ 4 Last Checked 1 month ago

Abstract

Counter-argument generation -- a captivating area in computational linguistics -- seeks to craft statements that offer opposing views. While most research has ventured into paragraph-level generation, sentence-level counter-argument generation beckons with its unique constraints and brevity-focused challenges. Furthermore, the diverse nature of counter-arguments poses challenges for evaluating model performance solely based on n-gram-based metrics. In this paper, we present the ArgTersely benchmark for sentence-level counter-argument generation, drawing from a manually annotated dataset from the ChangeMyView debate forum. We also propose Arg-LlaMA for generating high-quality counter-argument. For better evaluation, we trained a BERT-based evaluator Arg-Judge with human preference data. We conducted comparative experiments involving various baselines such as LlaMA, Alpaca, GPT-3, and others. The results show the competitiveness of our proposed framework and evaluator in counter-argument generation tasks. Code and data are available at https://github.com/amazingljy1206/ArgTersely.