CogniRAG: Integrating Causal Hyperedges and Counterfactual Reasoning for Knowledge-Intensive Tasks

Abstract

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources. Yet, existing chunk- or graph-based frameworks remain confined to surface-level semantic correlations, lacking the capacity to model mechanistic causality, cross-document dependencies, and counterfactual reasoning. To address these limitations, this study introduces CogniRAG, a causal reasoning–centric RAG framework that systematically transforms retrieval into a structured process of causal inference. CogniRAG encodes four specialized causal hyperedge types—Linear Chain, Feedback Loop, Intervention Point, and System Stability—within a unified CogniGraphDB, enabling multi-entity causal tracing and intervention analysis. A dual retrieval strategy combining entity diffusion and relation expansion constructs causally enriched prompts that enhance inferential depth beyond conventional similarity-based retrieval. Experiments conducted across four knowledge-intensive domains (Medicine, Political Science, Computer Science, Finance) using an identical LLaMA-3.1-70B backbone and 480 systematically generated questions demonstrate consistent and statistically robust improvements. CogniRAG achieves an approximately five-percentage-point Overall gain over HyperRAG across all domains (for example, Medicine 78.67 vs 73.63), with the largest increases observed in Empowerment and Logical Coherence, corroborated by objective reliability metrics (+1.8 pp Faithfulness, +1.2 pp Factual Consistency, −0.7 pp Hallucination). Cross-backbone evaluation with Qwen-Plus and Mistral Large 2 confirms backbone-agnostic consistency (+3–5 pp), while efficiency analysis reveals moderate computational overheads (indexing +30–40%; latency +50%) proportional to added causal reasoning depth. Overall, CogniRAG advances RAG from semantic retrieval toward causal, counterfactual, and interpretable knowledge reasoning, with future work focusing on real-time causal-graph updating, multimodal evidence integration, reproducible benchmarking, and meta-reasoning for confidence calibration to strengthen scalability and external validity.