pith. sign in

Ranked voting based self-consistency of large language models.arXiv preprint arXiv:2505.10772,

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.CR 1

years

2026 2

verdicts

UNVERDICTED 2

clear filters

representative citing papers

Inference Time Optimization with Confidence Dynamics

cs.CL · 2026-05-24 · unverdicted · novelty 6.0

Correct reasoning traces exhibit positive confidence gain while incorrect traces show declining confidence, enabling CDG-based voting that boosts performance on AIME, HMMT and BRUMO benchmarks across multiple LLM architectures.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Inference Time Optimization with Confidence Dynamics cs.CL · 2026-05-24 · unverdicted · none · ref 14

    Correct reasoning traces exhibit positive confidence gain while incorrect traces show declining confidence, enabling CDG-based voting that boosts performance on AIME, HMMT and BRUMO benchmarks across multiple LLM architectures.