CIP: A Plug-and-Play Causal Prompting Framework for Mitigating Hallucinations under Long-Context Noise

TL;DR

CIP is a causal prompting framework that reduces hallucinations in large language models by guiding reasoning with causal relations, improving factual accuracy, interpretability, and efficiency across various models.

Contribution

The paper introduces CIP, a novel plug-and-play causal prompting method that mitigates hallucinations by injecting causal relations into prompts, enhancing reasoning and factual grounding.

Findings

Consistent improvement in reasoning quality across seven language models.

Significant reduction in response latency by up to 55.1%.

Fourfold increase in effective information density.

Abstract

Large language models often hallucinate when processing long and noisy retrieval contexts because they rely on spurious correlations rather than genuine causal relationships. We propose CIP, a lightweight and plug-and-play causal prompting framework that mitigates hallucinations at the input stage. CIP constructs a causal relation sequence among entities, actions, and events and injects it into the prompt to guide reasoning toward causally relevant evidence. Through causal intervention and counterfactual reasoning, CIP suppresses non causal reasoning paths, improving factual grounding and interpretability. Experiments across seven mainstream language models, including GPT-4o, Gemini 2.0 Flash, and Llama 3.1, show that CIP consistently enhances reasoning quality and reliability, achieving 2.6 points improvement in Attributable Rate, 0.38 improvement in Causal Consistency Score, and a fourfold increase in effective information density. API level profiling further shows that CIP accelerates contextual understanding and reduces end to end response latency by up to 55.1 percent. These results suggest that causal reasoning may serve as a promising paradigm for improving the explainability, stability, and efficiency of large language models.