按任务动态删层，让大模型更省力更高效。
TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination
- 推理时根据任务自动剔除无关层，生成定制化结构。
- 9个任务上性能不降反升，计算量显著减少。
- 无需重训，适合实际部署，兼容微调提升效果。
大型语言模型通常采用固定架构，但越来越多证据表明并非所有层对每个下游任务都同等重要。我们提出TALE（任务感知层消除）方法，在推理阶段通过选择性移除对特定任务无用或有害的层，提升任务表现。TALE优化任务特异性性能，实现无需重训的任务定制化架构。在9个任务和5个模型家族中，无论零样本还是少样本设置下，TALE均保持或超越基线性能，同时降低计算成本。该方法还与微调协同增效，进一步提升表现。计算新任务的TALE仅需少量资源，是可实用、可部署的任务专用大模型推理方案。
原文摘要 · Abstract (English)
Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to every downstream task. We introduce TALE (Task-Aware Layer Elimination), an inference-time method that improves task performance by selectively removing layers that are irrelevant or detrimental for a given task. TALE optimizes task-specific performance, yielding a task-optimized architecture without retraining. Across 9 tasks and 5 model families, under both zero-shot and few-shot settings, TALE consistently matches or surpasses baseline performance while simultaneously reducing computational costs. TALE also synergizes with fine-tuning, leading to further performance improvements. Computing TALE for a new task requires modest resources, making it a practical and deployable solution for task-specialized LLM inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。