Research map / Probabilistic and scientific modeling / Molecules and proteins
Strategic Sequences of Arguments for Persuasion Using Decision Trees
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use MaxiMax instead of other rules when divergence between profile and persuadee is low | decision rule · Random persuasion graphs, 8 arguments | average outcome | Helped |
| Use Hurwicz alpha=0.8 instead of MaxiMax | persuasion decision rule · Random persuasion graphs | average outcome | Mixed |
| Use MaxiMin or Hurwicz alpha=0.2 when divergence is large | persuasion decision rule · Random persuasion graphs | average outcome | Helped |
| Use Hurwicz rule instead of MaxiMin | persuasion decision rule · Random persuasion graphs | average outcome | Helped |
| Use Laplace or Hurwicz alpha=0.5 averaging rules | persuasion decision rule · Random persuasion graphs | average outcome | Helped |
| Vary divergence error on naive random rule | random decision rule · Random persuasion graphs | average outcome | No clear effect |
| Increase dialogue horizon (2 to 8) for MaxiMax | MaxiMax · Random persuasion graphs | average outcome | Mixed |
| Choose MaxiMax over MaxiMin on example tree | MaxiMax vs MaxiMin · Example tree Table 1 | chosen action: 3 vs -10 | Mixed |
Closest papers by meaning
- Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters (ICLR 2026 · similarity 0.85)
- Markov Persuasion Processes: Learning to Persuade From Scratch (NeurIPS 2025 · similarity 0.85)
- Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action (NeurIPS 2026 · similarity 0.84)
- Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models? (NeurIPS 2025 · similarity 0.84)
- Persuasive Prediction via Decision Calibration (NeurIPS 2026 · similarity 0.84)
- Multi-LLM Debate: Framework, Principals, and Interventions (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.