HalluClean: A Unified Framework to Combat Hallucinations in LLMs
This addresses the issue of factual unreliability in LLM outputs for users in natural language processing applications, though it is incremental as it builds on existing reasoning-enhanced paradigms.
The paper tackles the problem of hallucinated content in large language models (LLMs) by introducing HalluClean, a lightweight and task-agnostic framework for detecting and correcting hallucinations, which significantly improves factual consistency across five tasks and outperforms baselines.
Large language models (LLMs) have achieved impressive performance across a wide range of natural language processing tasks, yet they often produce hallucinated content that undermines factual reliability. To address this challenge, we introduce HalluClean, a lightweight and task-agnostic framework for detecting and correcting hallucinations in LLM-generated text. HalluClean adopts a reasoning-enhanced paradigm, explicitly decomposing the process into planning, execution, and revision stages to identify and refine unsupported claims. It employs minimal task-routing prompts to enable zero-shot generalization across diverse domains, without relying on external knowledge sources or supervised detectors. We conduct extensive evaluations on five representative tasks-question answering, dialogue, summarization, math word problems, and contradiction detection. Experimental results show that HalluClean significantly improves factual consistency and outperforms competitive baselines, demonstrating its potential to enhance the trustworthiness of LLM outputs in real-world applications.