This work suggests fundamentally rethinking the current practice of pruning large language models (LLMs). The way it is done is by divide and conquer: split the model into submodels, sequentially prune them, and reconstruct predictions of the dense counterparts on small calibration data one at a time; the final model is obtained simply by putting the resulting sparse submodels together. While this approach enables pruning under memory constraints, it generates high reconstruction errors. In this work, we first present an array of reconstruction techniques that can significantly reduce this error by more than 90%. Unwittingly, however, we discover that minimizing reconstruction error is not always ideal and can overfit the given calibration data, resulting in rather increased language perplexity and poor performance at downstream tasks. We find out that a strategy of self-generating calibration data can mitigate this trade-off between reconstruction and generalization, suggesting new directions in the presence of both benefits and pitfalls of reconstruction for pruning LLMs.
Despite recent advances in LLM quantization, activation quantization remains to be challenging due to the activation outliers. Conventional remedies, e.g., mixing precisions for different channels, introduce extra overhead and reduce the speedup. In this work, we develop a simple yet effective strategy to facilitate per-tensor activation quantization by preventing the generation of problematic tokens. Precisely, we propose a method to find a set of key-value cache, coined _CushionCache_, which mitigates outliers in subsequent tokens when inserted as a prefix. CushionCache works in two steps: First, we greedily search for a prompt token sequence that minimizes the maximum activation values in subsequent tokens. Then, we further tune the token cache to regularize the activations of subsequent tokens to be more quantization-friendly. The proposed method successfully addresses activation outliers of LLMs, providing a substantial performance boost for per-tensor activation quantization methods. We thoroughly evaluate our method over a wide range of models and benchmarks and find that it significantly surpasses the established baseline of per-tensor W8A8 quantization and can be seamlessly integrated with the recent activation quantization method.
Recent advances in named entity recognition (NER) have pushed the boundary of the task to incorporate visual signals, leading to many variants, including multi-modal NER (MNER) or grounded MNER (GMNER). A key challenge to these tasks is that the model should be able to generalize to the entities unseen during the training, and should be able to handle the training samples with noisy annotations.To address this obstacle, we propose SCANNER (Span CANdidate detection and recognition for NER), a model capable of effectively handling all three NER variants.SCANNER is a two-stage structure; we extract entity candidates in the first stage and use it as a query to get knowledge, effectively pulling knowledge from various sources.We can boost our performance by utilizing this entity-centric extracted knowledge to address unseen entities.Furthermore, to tackle the challenges arising from noisy annotations in NER datasets, we introduce a novel self-distillation method, enhancing the robustness and accuracy of our model in processing training data with inherent uncertainties.Our approach demonstrates competitive performance on the NER benchmark and surpasses existing methods on both MNER and GMNER benchmarks.Further analysis shows that the proposed distillation and knowledge utilization methods improve the performance of our model on various benchmarks.