Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises
This work addresses robustness and explainability issues in RAG systems for knowledge-intensive tasks, representing an incremental improvement.
The paper tackles the problem of incomplete evidence in Retrieval-Augmented Generation (RAG) systems by integrating abductive inference to generate and validate missing premises, resulting in improved answer accuracy and reasoning faithfulness on benchmarks.
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.