Large Language Models (LLMs) frequently produce factually inaccurate outputs—a phenomenon known as hallucination, which limits their accuracy in knowledge-intensive NLP tasks. Retrieval-augmented generation and agentic frameworks such as Reasoning and Acting (ReAct) can address this by giving the model access to external knowledge. However, LLMs often fail to remain faithful to the retrieved information.
We present a systematic analysis of how combining the ReAct framework with decoding strategies (i.e., DeCoRe, DoLa, and CAD) can influence the faithfulness of LLM-generated answers. Our results show that combining an agentic framework for knowledge retrieval with decoding methods can increase accuracy on Multi-Hop Question Answering tasks, observing an F1 increase from 19.5 to 32.6 on HotpotQA.