Tootfinder

TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax
Tobias Christian Nauen, Sebastian Palacio, Andreas Dengel
https://arxiv.org/abs/2403.02920

TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax
The quadratic complexity of the attention mechanism represents one of the biggest hurdles for processing long sequences using Transformers. Current methods, relying on sparse representations or stateful recurrence, sacrifice token-to-token interactions, which ultimately leads to compromises in performance. This paper introduces TaylorShift, a novel reformulation of the Taylor softmax that enables computing full token-to-token interactions in linear time and space. We analytically determine the …

Fairly Evaluating Large Language Model-based Recommendation Needs Revisit the Cross-Entropy Loss
Cong Xu, Zhangchi Zhu, Jun Wang, Jianyong Wang, Wei Zhang
https://arxiv.org/abs/2402.06216

Fairly Evaluating Large Language Model-based Recommendation Needs Revisit the Cross-Entropy Loss
Large language models (LLMs) have gained much attention in the recommendation community; some studies have observed that LLMs, fine-tuned by the cross-entropy loss with a full softmax, could achieve state-of-the-art performance already. However, these claims are drawn from unobjective and unfair comparisons. In view of the substantial quantity of items in reality, conventional recommenders typically adopt a pointwise/pairwise loss function instead for training. This substitute however causes se…