Research map / Large language models / Retrieval and knowledge
Eliciting Thinking Hierarchy without a Prior
Yuqing Kong, Yunqi Li, Yubo Zhang, Zhihuan Huang, Jinzhao Wu
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 thinking-hierarchy algorithm instead of plurality voting | Plurality voting · Math | questions correct: 24 -> 29 | Improved |
| use thinking-hierarchy algorithm instead of plurality voting | Plurality voting · Go | questions correct: 23 -> 28 | Improved |
| use thinking-hierarchy algorithm instead of plurality voting | Plurality voting · General knowledge | questions correct: 35 -> 41 | Improved |
| use thinking-hierarchy algorithm instead of plurality voting | Plurality voting · Chinese character | questions correct: 34 -> 36 | Improved |
| use variant instead of default algorithm (ablation) | Default algorithm · Chinese character | questions correct: 36 -> 35 | Hurt |
| use variant instead of default algorithm (ablation) | Default algorithm · Math, Go, General knowledge | questions correct: 29 -> 29 | No clear effect |
| rank by lack-of-fit index as reliability | Thinking hierarchy algorithm · all questions | lack-of-fit | Improved |
Closest papers by meaning
- MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning? (NeurIPS 2025 · similarity 0.81)
- Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization (NeurIPS 2026 · similarity 0.81)
- The Surprising Effectiveness of SP Voting with Partial Preferences (NeurIPS 2024 · similarity 0.81)
- Debating with More Persuasive LLMs Leads to More Truthful Answers (ICML 2024 · similarity 0.80)
- When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning (NeurIPS 2026 · similarity 0.80)
- Representative Ranking for Deliberation in the Public Sphere (ICML 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.
