Papers
arxiv:2506.15787

SLR: An Automated Synthesis Framework for Scalable Logical Reasoning

Published on Jun 18
Authors:
,
,
,
,
,
,
,
,

Abstract

SLR is a framework for evaluating and training LLMs through scalable logical reasoning, creating a large benchmark that highlights the need for logic-tuning to improve logical inference without excessive computational cost.

AI-generated summary

We introduce SLR, an end-to-end framework for systematic evaluation and training of Large Language Models (LLMs) via Scalable Logical Reasoning. Given a user's task specification, SLR enables scalable, automated synthesis of inductive reasoning tasks with precisely controlled difficulty. For each task, SLR synthesizes (i) a latent ground-truth rule, (ii) an executable validation program used by a symbolic judge to deterministically verify model outputs, and (iii) an instruction prompt for the reasoning task. Using SLR, we create SLR-Bench, a benchmark comprising over 19k prompts spanning 20 curriculum levels that progressively increase in relational, arithmetic, and recursive complexity. Large-scale evaluation reveals that contemporary LLMs readily produce syntactically valid rules, yet often fail at correct logical inference. Recent reasoning LLMs do somewhat better, but incur substantial increases in test-time compute, sometimes exceeding 15k completion tokens. Finally, logic-tuning via SLR doubles Llama-3-8B accuracy on SLR-Bench, achieving parity with Gemini-Flash-Thinking at a fraction of computational cost. SLR is fully automated, requires no human annotation, ensures dataset novelty, and offers a scalable environment for probing and advancing LLMs' reasoning capabilities.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2506.15787 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 1

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.