Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises

TL;DR

This paper introduces a framework that incorporates abductive inference into retrieval-augmented language models to generate and validate missing premises, improving reasoning accuracy and robustness in knowledge-intensive tasks.

Contribution

It presents a novel method for detecting evidence gaps, generating plausible missing premises, and validating them within RAG systems, enhancing their reasoning capabilities.

Findings

Improved answer accuracy on abductive reasoning benchmarks

Enhanced reasoning faithfulness in multi-hop QA tasks

Demonstrated robustness of the approach in incomplete evidence scenarios

Abstract

Large Language Models (LLMs) enhanced with retrieval -- commonly referred to as Retrieval-Augmented Generation (RAG) -- have demonstrated strong performance in knowledge-intensive tasks. However, RAG pipelines often fail when retrieved evidence is incomplete, leaving gaps in the reasoning process. In such cases, \emph{abductive inference} -- the process of generating plausible missing premises to explain observations -- offers a principled approach to bridge these gaps. In this paper, we propose a framework that integrates abductive inference into retrieval-augmented LLMs. Our method detects insufficient evidence, generates candidate missing premises, and validates them through consistency and plausibility checks. Experimental results on abductive reasoning and multi-hop QA benchmarks show that our approach improves both answer accuracy and reasoning faithfulness. This work highlights abductive inference as a promising direction for enhancing the robustness and explainability of RAG systems.