Differential Transformer

Transformer tends to overallocate attention to irrelevant context. In this work, we introduce DIFF Transformer, which amplifies attention to the relevant context while canceling noise. Specifically, the differential attention mechanism calculates attention scores as the difference between two separate softmax attention maps. The subtraction cancels noise, promoting the emergence of sparse attention patterns. Experimental results on language modeling show that DIFF Transformer outperforms Transformer in various settings of scaling up model size and training tokens. More intriguingly, it offers notable advantages in practical applications, such as long-context modeling, key information retrieval, hallucination mitigation, in-context learning, and reduction of activation outliers. By being less distracted by irrelevant context, DIFF Transformer can mitigate hallucination in question answering and text summarization. For in-context learning, DIFF Transformer not only enhances accuracy but is also more robust to order permutation, which was considered as a chronic robustness issue. The results position DIFF Transformer as a highly effective and promising architecture to advance large language models.

Introduction. Transformer (Vaswani et al., 2017) has garnered significant research interest in recent years, with the decoder-only Transformer emerging as the de facto standard for large language models (LLMs). At the heart of Transformer is the attention mechanism, which employs the softmax function to weigh the importance of various tokens in a sequence. However, recent studies (Kamradt, 2023; Liu et al., 2024b) show that LLMs face challenges in accurately retrieving key information from context. As illustrated on the left side of Figure 1, we visualize the normalized attention scores assigned to different parts of the context by a Transformer. The task is to retrieve an answer embedded in the middle of a pile of documents. The visualization reveals that Transformer tends to allocate only a small proportion of attention scores to the correct answer, while disproportionately focusing on irrelevant context. The experiments in Section 3 further substantiate that Transformers struggle with such capabilities.

Discussion / Conclusion. In this work, we introduce Differential Transformer (a.k.a. DIFF Transformer), which amplifies attention to the relevant context while canceling noise. Experimental results on language modeling show that DIFF Transformer outperforms Transformer in terms of scaling properties, long-context modeling, key information retrieval, hallucination mitigation, in-context learning, and reduction of activation outliers. The results emphasize the importance of reducing attention noise. Moreover, the differential attention mechanism can be easily implemented with FlashAttention (Dao et al., 2022). The findings position DIFF Transformer as a distinctive and promising foundation architecture for large language models. In the future, we can develop efficient low-bit attention kernels due to the reduced magnitude of activation outliers. As the attention pattern becomes much sparser, we would also like to utilize the property to compress key-value caches.