Research map / Multi-agent systems and games / Human-AI and goal-conditioned
When Proxy Agents Disagree, Do Humans Mirror? Manipulating Human Behavior in Moral Dilemmas Through Agents
Haotian Deng, Sitian Wang, Ruxin Wang, Chen Wei, Quanying Liu
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 |
|---|---|---|---|
| fine-tune individually on each participant's data (IndivNet vs GroupNet) | BERT GroupNet · IndivData | accuracy: 60.2% -> 63.4% | Improved |
| fine-tune individually on each participant's data | BERT GroupNet · GroupData | accuracy: 59.5% -> 59.6% | No clear effect |
| individual fine-tuning | BERT GroupNet · human uncertainty alignment | Spearman correlation: 0.01 -> 0.13 | Improved |
| individual fine-tuning | BERT GroupNet · low and medium uncertainty dilemmas | accuracy | Hurt |
| individual fine-tuning | BERT GroupNet · high uncertainty dilemmas | accuracy | Improved |
| select stimuli with fine-tuned individual agents instead of zero-shot model | stimulus selection · human intervention experiment | guidance outcome: 6% average improvement | Improved |
| select stimuli with fine-tuned individual agents instead of zero-shot model | stimulus selection · human intervention experiment | target ratio: 29% improvement | Improved |
| higher human uncertainty level | dilemma groups · BJSD analysis | mean BJSD: 0.0205 -> 0.0245 | Improved |
Closest papers by meaning
- LLM Agents Can Be Choice-Supportive Biased Evaluators: An Empirical Study (AAAI 2025 · similarity 0.89)
- Many LLMs Are More Utilitarian Than One (NeurIPS 2025 · similarity 0.88)
- Large Language Models Assume People are More Rational than We Really are (ICLR 2025 · similarity 0.88)
- Learning Human-like Representations to Enable Learning Human Values (NeurIPS 2024 · similarity 0.88)
- Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties (AAAI 2024 · similarity 0.87)
- Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback (ICML 2024 · similarity 0.87)
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.
