self-consistency

Tag

Cards List
#self-consistency

KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning

arXiv cs.AI · 3d ago Cached

KACE introduces a knowledge-adaptive context engineering method that separates storage from usage via an epistemic tree and tiered self-consistency, achieving 62.2% on AIME 2025—a 10.4-point gain over fixed self-consistency.

0 favorites 0 likes
#self-consistency

Beyond Consensus: Trace-Level Synthesis in Mixture of Agents

arXiv cs.AI · 2026-05-29 Cached

This paper reveals that aggregating complete reasoning traces from multiple LLM agents, rather than just their final answers, can correct errors even when agents unanimously agree, introducing the 'aggregation paradox' and the Self-Consistent Mixture of Agents method.

0 favorites 0 likes
#self-consistency

Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency

arXiv cs.CL · 2026-05-22 Cached

This paper proposes a self-supervised framework using multilingual self-consistency and a self-critique mechanism to transfer cultural knowledge across languages, achieving a 5.03% average improvement on English queries in the BLEnD benchmark by surfacing latent cultural knowledge from local-language representations.

0 favorites 0 likes
#self-consistency

Reliable Chain-of-Thought via Prefix Consistency

Hugging Face Daily Papers · 2026-05-08 Cached

This paper introduces 'prefix consistency,' a method that weights candidate responses in Chain-of-Thought reasoning based on answer reproduction rates during trace regeneration. It achieves high accuracy with significantly fewer tokens than standard majority voting across various reasoning models and benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback