Town Hall Debate Prompting: Enhancing Logical Reasoning in LLMs through Multi-Persona Interaction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915166406311936 |
|---|---|
| author | Sandwar, Vivaan Jain, Bhav Thangaraj, Rishan Garg, Ishaan Lam, Michael Zhu, Kevin |
| author_facet | Sandwar, Vivaan Jain, Bhav Thangaraj, Rishan Garg, Ishaan Lam, Michael Zhu, Kevin |
| contents | Debate is a commonly used form of human communication catered towards problem-solving because of its efficiency. Debate fundamentally allows multiple viewpoints to be brought up in problem-solving, and for complex problems, each viewpoint opens a new path for problem-solving. In this work, we apply this concept to LLM decision-making by proposing town hall-style debate prompting (THDP), a prompting method that splices a language model into multiple personas that will debate one another to reach a conclusion. Our experimental pipeline varies both the number of personas and the personality types of each persona to find the optimum town hall size and personality for benchmark performance as measured by ZebraLogic bench, a reasoning-intensive benchmark characterized by both multiple-choice and fill-in-the-blank questions. Our experimental results demonstrate that a town hall size of 5 personas with LLM-determined personality types performs optimally on ZebraLogic, achieving a 13\% improvement over one-shot CoT baselines in per-cell accuracy in GPT-4o, 9% puzzle accuracy increase in Claude 3.5 Sonnet, and an improvement in hard puzzle accuracy from 10-15%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15725 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Town Hall Debate Prompting: Enhancing Logical Reasoning in LLMs through Multi-Persona Interaction Sandwar, Vivaan Jain, Bhav Thangaraj, Rishan Garg, Ishaan Lam, Michael Zhu, Kevin Computation and Language Debate is a commonly used form of human communication catered towards problem-solving because of its efficiency. Debate fundamentally allows multiple viewpoints to be brought up in problem-solving, and for complex problems, each viewpoint opens a new path for problem-solving. In this work, we apply this concept to LLM decision-making by proposing town hall-style debate prompting (THDP), a prompting method that splices a language model into multiple personas that will debate one another to reach a conclusion. Our experimental pipeline varies both the number of personas and the personality types of each persona to find the optimum town hall size and personality for benchmark performance as measured by ZebraLogic bench, a reasoning-intensive benchmark characterized by both multiple-choice and fill-in-the-blank questions. Our experimental results demonstrate that a town hall size of 5 personas with LLM-determined personality types performs optimally on ZebraLogic, achieving a 13\% improvement over one-shot CoT baselines in per-cell accuracy in GPT-4o, 9% puzzle accuracy increase in Claude 3.5 Sonnet, and an improvement in hard puzzle accuracy from 10-15%. |
| title | Town Hall Debate Prompting: Enhancing Logical Reasoning in LLMs through Multi-Persona Interaction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.15725 |