Research map / Large language models / Language, safety and interpretability
Verbalized Bayesian Persuasion
Wenhao Li, Yue Lin, Yun Hua, Xiangfeng Wang, Bo Jin, Hongyuan Zha, Baoxiang Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add obedience constraint (ablation) | VBP · General static BP (S2) | lying probability | Improved |
| add verbalized commitment assumption (ablation) | VBP · General static BP (S2) | lying probability | No clear effect |
| add information obfuscation (ablation) | VBP · General static BP (S2) | lying probability | No clear effect |
| prune strategy pool to fewer prompts (ablation) | Prompt-PSRO · General static BP (S2) | sender lying probability | Hurt |
| use unaligned LLaMA instead of aligned LLM as base model (ablation) | VBP · Classic static BP (S1) | honesty probability | Hurt |
| add receiver memory of history (multistage S3 vs S2) | VBP · Multistage BP (S3) | sender/receiver reward | Hurt |
| remove signal polarization (S1 to S2) | VBP · Classic static BP | performance | Hurt |
Closest papers by meaning
- Markov Persuasion Processes: Learning to Persuade From Scratch (NeurIPS 2025 · similarity 0.87)
- Online Bayesian Persuasion Without a Clue (NeurIPS 2024 · similarity 0.86)
- Persuasive Prediction via Decision Calibration (NeurIPS 2026 · similarity 0.86)
- Improving Cooperation in Language Games with Bayesian Inference and the Cognitive Hierarchy (AAAI 2025 · similarity 0.86)
- Bayesian Persuasion with Externalities: Exploiting Agent Types (AAAI 2025 · similarity 0.85)
- Learning to Persuade a Biased Receiver (NeurIPS 2026 · similarity 0.85)
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.
