Multidimensional Consistency Improves Reasoning in Language Models

arXiv:2503.02670 · cs.CL · Submitted 2025-03-04 · Read on arXiv

cs.CL

Submitted: 2025-03-04

Updated: 2026-10-13

Comments: Accepted to AACL 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 6× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 8 episodes

Sources

• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• On the Opportunities and Risks of Foundation Models
• Progressive-Hint Prompting Improves Reasoning in Large Language Models
• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• Rationale-Augmented Ensembles in Language Models
• Qwen2 Technical Report
• Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
• Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering