Research map / Large language models / AI and society
Intelligent Advice Provisioning for Repeated Interaction
Priel Levy, David Sarne
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 |
|---|---|---|---|
| use S-Gradual (gradual drift from intuitive to optimal advice) instead of other advisors | advisor in repeated Car Purchasing Game · Car Purchasing Game | average profit: 55%-71% improvement in average profit | Improved |
| use S-Aggregate (regret-like weighted advice) instead of other advisors | advisor in repeated Car Purchasing Game · Car Purchasing Game | general user satisfaction: 32%-50% improvement | Improved |
| use suboptimal advice (S-Gradual) instead of always giving optimal advice | advisor · Car Purchasing Game | advice adoption rate: 25% -> 38% | Improved |
| use S-Aggregate instead of S-Elmalech | advisor · Car Purchasing Game | advice adoption rate: 35% -> 37% | Improved |
| use single-shot suboptimal advisor S-Elmalech in repeated setting vs optimal advisor | advisor · Car Purchasing Game | average profit | Hurt |
| use S-Elmalech suboptimal advice instead of optimal advice | advisor · Car Purchasing Game | user satisfaction (recommend, use again) | Improved |
| any advisor vs no advisor on users' own initial offers | user offers · Car Purchasing Game | average initial offer, early vs late games | No clear effect |
Closest papers by meaning
- Learning to Make Adherence-aware Advice (ICLR 2024 · similarity 0.84)
- How do Large Language Models Navigate Conflicts between Honesty and Helpfulness? (ICML 2024 · similarity 0.80)
- PersonalLLM: Tailoring LLMs to Individual Preferences (ICLR 2025 · similarity 0.80)
- On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback (ICLR 2025 · similarity 0.80)
- BLEUBERI: BLEU is a surprisingly effective reward for instruction following (NeurIPS 2025 · similarity 0.80)
- Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward (NeurIPS 2025 · similarity 0.80)
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.
