# PTCG: Persona-guided Tree-based Counterargument Generation

arXiv: https://arxiv.org/abs/2609.07120 · HTML: https://mlsanity.com/paper/2609.07120/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 53 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [Virtual Personas for Language Models via an Anthology of Backstories](https://mlsanity.com/paper/2407.06576/) (2024)
- [Exploring the Potential of Large Language Models in Computational Argumentation](https://mlsanity.com/paper/2311.09022/) (2023)
- [Modifying Large Language Model Post-Training for Diverse Creative Writing](https://mlsanity.com/paper/2503.17126/) (2025)
- [Argument Strength is in the Eye of the Beholder: Audience Effects in Persuasion](https://mlsanity.com/paper/1708.09085/) (2017)
- [Neural Argument Generation Augmented with Externally Retrieved Evidence](https://mlsanity.com/paper/1805.10254/) (2018)
- [Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation](https://mlsanity.com/paper/2406.19643/) (2024)
- [Exploring the Role of Argument Structure in Online Debate Persuasion](https://mlsanity.com/paper/2010.03538/) (2020)
- [A Corpus for Modeling User and Language Effects in Argumentation on Online Debating](https://mlsanity.com/paper/1906.11310/) (2019)
- [Argument Undermining: Counter-Argument Generation by Attacking Weak Premises](https://mlsanity.com/paper/2105.11752/) (2021)
- [Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation](https://mlsanity.com/paper/2312.13608/) (2023)
- [The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses](https://mlsanity.com/paper/2411.06008/) (2024)
- [PsyPlay: Personality-Infused Role-Playing Conversational Agents](https://mlsanity.com/paper/2502.03821/) (2025)
- [AMERICANO: Argument Generation with Discourse-driven Decomposition and Agent Interaction](https://mlsanity.com/paper/2310.20352/) (2023)
- [Mitigating Manipulation and Enhancing Persuasion: A Reflective Multi-Agent Approach for Legal Argument Generation](https://mlsanity.com/paper/2506.02992/) (2025)
- [From Argumentation to Deliberation: Perspectivized Stance Vectors for Fine-grained (Dis)agreement Analysis](https://mlsanity.com/paper/2502.09644/) (2025)

## Abstract (arXiv)

The ability to generate counterarguments is important for critical thinking and balanced discourse, yet existing approaches typically produce only a single counterargument, failing to capture the diversity and persuasiveness required in real-world debates. To address this limitation, we propose Persona-guided Tree-based Counterargument Generation (PTCG), a framework that combines Tree-of-Thoughts-inspired step-wise generation and pruning with speaker persona selection. By estimating the author's persona from the original argument and incorporating speaker personas representing distinct perspectives, PTCG operationalizes perspective-taking and enables the generation of diverse counterarguments. Results from LLM-as-a-Judge, classifier-based assessment, and human evaluations indicate that PTCG shows consistent improvements in both the diversity and persuasiveness of counterarguments compared to baseline methods.