Compressing high-capability Large Language Models (LLMs) has emerged as a favored strategy for resource-efficient inferences. While state-of-the-art (SoTA) compression methods boast impressive advancements in preserving benign task performance, the potential risks of compression in terms of safety and trustworthiness have been largely neglected. This study conducts the first, thorough evaluation of three (3) leading LLMs using five (5) SoTA compression techniques across eight (8) trustworthiness dimensions. Our experiments highlight the intricate interplay between compression and trustworthiness, revealing some interesting patterns. We find that quantization is currently a more effective approach than pruning in achieving efficiency and trustworthiness simultaneously. For instance, a 4-bit quantized model retains the trustworthiness of its original counterpart, but model pruning significantly degrades trustworthiness, even at 50% sparsity. Moreover, employing quantization within a moderate bit range could unexpectedly improve certain trustworthiness dimensions such as ethics and fairness. Conversely, extreme quantization to very low bit levels (3 bits) tends to reduce trustworthiness significantly. This increased risk cannot be uncovered by looking at benign performance alone, in turn, mandating comprehensive trustworthiness evaluation in practice. These findings culminate in practical recommendations for simultaneously achieving high utility, efficiency, and trustworthiness in LLMs. Code and models are available at https://decoding-comp-trust.github.io.

翻译：压缩高能力大语言模型已成为资源高效推理的首选策略。尽管最先进的压缩方法在保持良性任务性能方面取得了显著进展，但压缩在安全性和可信度方面的潜在风险在很大程度上被忽视了。本研究首次对三种领先的大语言模型，采用五种最先进的压缩技术，在八个可信度维度上进行了全面评估。我们的实验揭示了压缩与可信度之间复杂的相互作用，并发现了一些有趣的规律。我们发现，在同时实现效率和可信度方面，量化是目前比剪枝更有效的方法。例如，4位量化模型保持了其原始版本的可信度，但模型剪枝即使在50%稀疏度下也会显著降低可信度。此外，在适中比特范围内采用量化可能会意外地提升某些可信度维度，如伦理性和公平性。相反，极端量化至极低比特水平（3位）往往会显著降低可信度。这种增加的风险无法仅通过观察良性性能来发现，因此在实际应用中需要进行全面的可信度评估。这些发现最终为在大语言模型中同时实现高实用性、高效率和可信度提出了实用建议。代码和模型可在 https://decoding-comp-trust.github.io 获取。