pith. sign in

Title resolution pending

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

2 Pith papers citing it

fields

cs.CL 2

years

2025 1 2024 1

representative citing papers

LIMO: Less is More for Reasoning

cs.CL · 2025-02-05 · unverdicted · novelty 6.0

LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.

citing papers explorer

Showing 2 of 2 citing papers.

  • Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models cs.CL · 2024-10-10 · conditional · none · ref 6

    Omni-MATH supplies 4428 human-verified Olympiad math problems that expose top LLMs achieving only 52.55% to 60.54% accuracy on the most difficult items.

  • LIMO: Less is More for Reasoning cs.CL · 2025-02-05 · unverdicted · none · ref 133

    LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.