The paper formalizes multi-path LLM reasoning as a diversity combining problem from wireless communications. It shows that the pairwise correlation of path correctness caps the effective sample size of majority voting, explaining why accuracy gains saturate as more reasoning paths are added. The authors derive an Adaptive-K rule that uses just four paths as a pilot to select the optimal number of paths, retaining 96-103% of the accuracy achieved with 32 paths across math, QA, and NLU benchmarks. This is interesting because it provides a theoretical explanation for saturation and a practical way to reduce compute without losing accuracy.
Correlated reasoning paths limit the gain from adding more LLM reasoning branches.
Analogy from wireless communications shows that pairwise correctness correlation caps effective sample size, and prompt diversity reduces correlation across 12 benchmarks.
Research Lab
Guangsheng Yu · Litianyi Zhang · Qin Wang · Xu Wang · Mingyuan Li · Shaoxiong Ji · +2 more
University of Technology Sydney · The University of Sydney · CSIRO · ELLIS Institute Finland · University of Turku
Research Digest··3 min read
In one line
Pairwise correlation of path correctness limits self-consistency gains, and an Adaptive-K rule from a four-path pilot retains full accuracy.
Before you read this
An idea this paper builds onRead it as
The authors formalize multi-path LLM reasoning as a diversity combining problem.
The authors introduced a framework adapting the design-effect and participation-ratio from statistics to model path correlation in multi-path LLM reasoning.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.