剪枝权重但不剪枝真相：在大语言模型剪枝时保障真实性
Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs
AI总结：
该研究发现LLM剪枝会破坏测谎关键的内部激活特征，提出逐层异常值对齐的真实性剪枝方法TPLO，同时优化TruthfulQA基准，在50%稀疏度下实现88%的幻觉检测准确率，兼顾剪枝效率与模型真实性保障。
摘要：
神经网络剪枝已成为在低资源场景下部署大语言模型（LLM）同时保留下游任务性能的一种有前景的方法。然而，我们首次揭示，这类剪枝会破坏LLM内部对测谎至关重要的激活特征——基于这些特征训练的探测分类器（通常是小型逻辑回归模型）可评估LLM生成陈述的真实性。这一发现提出了一个关键的开放性问题：我们如何在不牺牲这些关键测谎能力的前提下对LLM进行剪枝？我们的研究进一步表明，基于重要性朴素地调整逐层剪枝稀疏度会意外移除关键权重，尽管测谎依赖于LLM最重要的层，但这种调整仍无法提升测谎性能。为解决这一问题，我们提出了**逐层异常值对齐的真实性剪枝（Truthful Pruning aligned by Layer-wise Outliers, TPLO）**，该方法同时对激活异常值更多、判别特征更强的层给予更高重视。这一方法在保留LLM原有性能的同时，留存了实现鲁棒测谎所需的内部状态关键特征。此外，我们提出了一种提示规则来丰富TruthfulQA基准，以更好地校准LLM剪枝。实验结果表明，我们的方法提升了剪枝后LLM的幻觉检测能力（在50%稀疏度下达到88%的准确率），并增强了其在TruthfulQA上的性能。
英文摘要：
Neural network pruning has emerged as a promising approach for deploying LLMs in low-resource scenarios while preserving downstream task performance. However, for the first time, we reveal that such pruning disrupts LLMs' internal activation features crucial for lie detection, where probing classifiers (typically small logistic regression models) trained on these features assess the truthfulness of LLM-generated statements. This discovery raises a crucial open question: how can we prune LLMs without sacrificing these critical lie detection capabilities? Our investigation further reveals that naively adjusting layer-wise pruning sparsity based on importance inadvertently removes crucial weights, failing to improve lie detection performance despite its reliance on the most crucial LLM layer. To address this issue, we propose Truthful Pruning aligned by Layer-wise Outliers (TPLO), which places greater emphasis on layers with more activation outliers and stronger discriminative features simultaneously. This preserves LLMs' original performance while retaining critical features of inner states needed for robust lie detection. Moreover, we introduce a prompting rule to enrich the TruthfulQA benchmark for better calibrating LLM pruning. Empirical results show that our approach improves the hallucination detection for pruned LLMs (achieving 88% accuracy at 50% sparsity) and enhances their performance on TruthfulQA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
