From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation

TL;DR

This paper introduces HBLR, a novel backward reasoning framework that combines selective symbolic translation with hypothesis-driven verification, significantly improving logical reasoning accuracy and efficiency in large language models.

Contribution

It presents a new backward reasoning approach integrating confidence-aware symbolic translation and reflection modules to enhance LLM reasoning capabilities.

Findings

HBLR outperforms baselines on five reasoning benchmarks.

The framework improves reasoning accuracy and efficiency.

Selective translation reduces semantic drift and hallucinations.

Abstract

Logical reasoning is a core challenge in natural language understanding and a fundamental capability of artificial intelligence, underpinning scientific discovery, mathematical theorem proving, and complex decision-making. Despite the remarkable progress of large language models (LLMs), most current approaches still rely on forward reasoning paradigms, generating step-by-step rationales from premises to conclusions. However, such methods often suffer from redundant inference paths, hallucinated steps, and semantic drift, resulting in inefficient and unreliable reasoning. In this paper, we propose a novel framework, Hypothesis-driven Backward Logical Reasoning (HBLR). The core idea is to integrate confidence-aware symbolic translation with hypothesis-driven backward reasoning. In the translation phase, only high-confidence spans are converted into logical form, such as First-Order Logic (FOL), while uncertain content remains in natural language. A translation reflection module further ensures semantic fidelity by evaluating symbolic outputs and reverting lossy ones back to text when necessary. In the reasoning phase, HBLR simulates human deductive thinking by assuming the conclusion is true and recursively verifying its premises. A reasoning reflection module further identifies and corrects flawed inference steps, enhancing logical coherence. Extensive experiments on five reasoning benchmarks demonstrate that HBLR consistently outperforms strong baselines in both accuracy and efficiency.