Large language models (LLMs) can sometimes generate inaccurate responses known as hallucinations, which can be problematic for tasks relying on the accuracy of model responses. The main reasons behind LLM hallucinations are LLMs' current inability to identify inaccuracies in their output and self-correct based on their own capabilities without external feedback. There are multiple strategies employed to combat LLM hallucinations, including prompting, fine-tuning, retrieval augmented generation, and custom-designed approaches targeting specific applications. These methods can help reduce the probability of AI hallucinations, but their efficiency depends on the type of hallucination they addressed, resources available, and other factors.