🛰️ Daily AI Frontier
‹ back to 2026-08-17

More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It

Research LLMs & Foundation Models

Ranking

Overall 82
Content 100
Popularity 41

Observed public metrics from 1 member.

Merged summary

TL;DR - Power Sampling can increase probability mass on correct reasoning trajectories yet reduce downstream accuracy by narrowing useful path coverage. A deformation-controlled, support-preserving alternative avoids this failure and improves multi-sample reasoning inference.

  • Standard Power Sampling caused self-consistency accuracy drops of up to 18.5 percentage points.
  • Fixed exponents create a “dose mismatch,” changing distributions unevenly across problems.
  • Global sharpening creates a “coverage mismatch,” suppressing moderate-probability reasoning paths despite high pass@k.
  • Weighted self-consistency with the repaired sampler reversed these losses under the same inference budget.

Sources (1)

More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It

arXiv cs.LG Haohui Yang, Jiaxing Sun, Xiujun Ma 2026-08-14 arXiv:2608.14420
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-14 14:22:54.932621 UTC

TL;DR - Power Sampling can increase probability mass on correct reasoning trajectories yet reduce downstream accuracy by narrowing useful path coverage. A deformation-controlled, support-preserving alternative avoids this failure and improves multi-sample reasoning inference.

  • Standard Power Sampling caused self-consistency accuracy drops of up to 18.5 percentage points.
  • Fixed exponents create a “dose mismatch,” changing distributions unevenly across problems.
  • Global sharpening creates a “coverage mismatch,” suppressing moderate-probability reasoning paths despite high pass@k.
  • Weighted self-consistency with the repaired sampler reversed these losses under the same inference budget.
item →