InductionBench: LLMs Fail in the Simplest Complexity Class

TL;DR

InductionBench is a new benchmark that reveals current large language models struggle with basic inductive reasoning tasks, exposing a significant gap in their reasoning capabilities beyond deductive tasks.

Contribution

The paper introduces InductionBench, the first benchmark specifically designed to evaluate inductive reasoning in LLMs, highlighting their limitations in simple inductive tasks.

Findings

LLMs perform poorly on basic inductive reasoning tasks

Current models excel in deductive reasoning but not in inductive reasoning

Inductive reasoning remains a challenging area for state-of-the-art LLMs

Abstract

Large language models (LLMs) have shown remarkable improvements in reasoning and many existing benchmarks have been addressed by models such as o1 and o3 either fully or partially. However, a majority of these benchmarks emphasize deductive reasoning, including mathematical and coding tasks in which rules such as mathematical axioms or programming syntax are clearly defined, based on which LLMs can plan and apply these rules to arrive at a solution. In contrast, inductive reasoning, where one infers the underlying rules from observed data, remains less explored. Such inductive processes lie at the heart of scientific discovery, as they enable researchers to extract general principles from empirical observations. To assess whether LLMs possess this capacity, we introduce InductionBench, a new benchmark designed to evaluate the inductive reasoning ability of LLMs. Our experimental findings reveal that even the most advanced models available struggle to master the simplest complexity classes within the subregular hierarchy of functions, highlighting a notable deficiency in current LLMs' inductive reasoning capabilities. Coda and data are available https://github.com/Wenyueh/inductive_reasoning_benchmark.