Research map / Large language models / Reasoning and chain of thought
D-FUSEr: Diverse Failure, Unified Success via Error-Distribution Shaping in LLM Reasoning
David D. Baek, Andrew Estornell, Yichi Zhang, Muhammad Faaiz Taufiq, Jean-Francois Ton, Jie Mei, Tao Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes D-FUSEr, which shapes the error distribution across LLM reasoning samples so that errors are diverse while successes are unified, to improve test-time scaling via majority vote and iterative refinement.
Problem
Test-time scaling methods (majority vote aggregation, self-reflection, multi-agent inference) depend on how errors are distributed across samples; concentrated errors degrade aggregation accuracy and refinement effectiveness.
Approach
Shape the error distribution across sampled solutions: encourage diverse failures and unified successes, rather than only raising raw per-sample accuracy.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add diverse failure reward to distributional-reflection training (ablation) | Dist-Reflect (Qwen2.5-14B) · MMLU-Pro (OOD) | majority-vote accuracy (%): 70.1 -> 73.5 | Improved |
| add diverse failure reward to distributional-reflection training (ablation) | Dist-Reflect (Qwen2.5-14B) · RBENCH (OOD) | majority-vote accuracy (%): 60.9 -> 65.6 | Improved |
| add diverse failure reward to distributional-reflection training (ablation) | Dist-Reflect (Qwen2.5-14B) · BBH (OOD) | majority-vote accuracy (%): 88.2 -> 91.9 | Improved |
| add diverse failure reward to distributional-reflection training (ablation) | Dist-Reflect (Qwen2.5-14B) · GPQA (OOD) | majority-vote accuracy (%): 49.2 -> 48.9 | No clear effect |
| add diverse failure reward to distributional-reflection training (ablation) | Dist-Reflect (Llama-3.1-8B) · RBENCH (OOD) | majority-vote accuracy (%): 37.9 -> 54.9 | Improved |
| add diverse failure reward to distributional-reflection training (ablation) | Dist-Reflect (Llama-3.1-8B) · GPQA (OOD) | majority-vote accuracy (%): 33.8 -> 45.8 | Improved |
| use D-FUSEr instead of GRPO training | GRPO (Gemma-2-2B) · GPQA (OOD) | majority-vote accuracy (%): 29.6 -> 37.7 | Improved |
| add theoretical dynamic anti-votes at aggregation (ablation) | majority vote (Qwen2.5-3B) · RBENCH | majority-vote accuracy (%): 39.3 -> 48.3 | Improved |
| add fixed-strength anti-votes at aggregation (ablation) | majority vote (Qwen2.5-7B) · RBENCH | majority-vote accuracy (%): 50.1 -> 50.4 | No clear effect |
| add diverse failure reward to distributional-reflection training (ablation) | Dist-Reflect (Llama-8B) · BBH (OOD) | average accuracy (%): 69.8 -> 62.2 | Hurt |
| train with distributional reflection instead of Reflect-GRPO / GRPO | GRPO (Qwen-14B) · RBENCH (OOD) | majority-vote accuracy (%): 51.7 -> 60.9 | Improved |
Closest papers by meaning
- When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning (NeurIPS 2026 · similarity 0.89)
- A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning (NeurIPS 2025 · similarity 0.89)
- Reliable Chain-of-Thought via Prefix Consistency (NeurIPS 2026 · similarity 0.88)
- Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity (ICLR 2026 · similarity 0.87)
- GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements (ICML 2024 · similarity 0.87)
- R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training (ICML 2026 · 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.
