HypoBootstrap: A Bootstrapping Framework for Inductive Reasoning

Si Chen, Yifei Li, Richong Zhang

Keywords: inductive reasoning, inductive logic, hypothesis generation, hypothesis confirmation

Abstract:

Inductive reasoning infers general rules from observed evidence, which is one of the most critical intelligence abilities.
Previous works have succeeded in formal languages but suffer from onerous and error-prone conversions between a particular formal language and the working language.
As large language models (LLMs) have emerged, direct reasoning with various kinds of languages, especially natural languages, without formal language involvement has become feasible.
However, existing LLM-based inductive reasoning usually relies on LLM's intrinsic generation ability, which is prone to LLM's hallucination and lacks systematic guidance according to the nature of inductive reasoning.
To this end, we propose HypoBootstrap, an integrated framework for inductive reasoning that generates and confirms hypotheses both in a bootstrapping manner.
Regarding hypothesis generation, we propose a novel bootstrapping generation strategy, bootstrapping object hypotheses, relational hypotheses, and functional hypotheses successively, which assists LLM in observing the evidence from trivial patterns to non-trivial patterns.
Regarding hypothesis confirmation, we utilize Glymour's theory of bootstrap confirmation, a hypothesis confirmation theory from the philosophy of science that can confirm a set of hypotheses.
We use its principles to confirm the object hypotheses, relational hypotheses, and functional hypotheses.
Empirical studies on four inductive reasoning scenarios of different natures, involving causal induction, concept learning, grammar learning, and abstract reasoning, demonstrate that HypoBootstrap significantly outperforms existing methods.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 21293