prompt-repetition

LLMs are trained as Causal Language Models , where each token attends only to previous tokens . This leads to: Prompt repetition enables the second pass to reference the entire first pass, effectively mimicking some benefits of bidirectional attention . In the second repetition, the model reprocesses information across the entire first prompt and strengthens attention weights on key concepts , resulting in improved performance. Note : This does not change the model architecture to bidirectional; it is a prompt engineering technique to mitigate the limitations of causal models. Most dramatic improvement: Gemini 2.0 Flash-Lite on NameIndex: 21.33% → 97.33% (+76%p) Before: After (repetition ×2 applied): Expected output: Accuracy: original 78% → after repetition 93% (+15%p) Before: After (repetition ×3 applied): Prompt repeated 3 times Expected output: Accuracy: original 21% → after repetition 97% (+76%p) Note : Prompts containing tool call instructions are also repeated in their entirety . The full-repetition approach was adopted for implementation simplicity and consistency. Before: After (repetition ×2): Research results show that full repetition including tool call sections is also effective. Key insight: The prefill phase is highly parallelized on GPU, so doubling input tokens has minimal impact on latency.