提出高效层选择微调方法，用少量标注数据精准识别文本修订意图。
Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction
- 动态选关键层微调，按梯度大小筛选重要层，冻结冗余层。
- 在小规模修订语料上表现超基线，收敛快且显存占用低。
- 适合资源有限但需高精度修订分类的场景，如编辑辅助系统。
大语言模型（LLM）在文本生成任务中表现卓越，但在简单却重要的文本分类任务中潜力未被充分挖掘，因预训练更侧重生成而非分类。尽管指令微调可将分类转为生成任务，但对细微文本修改仍难准确判断。以文本修订为例，其涉及两段文本间的细微改动。直接微调LLM虽可行，但需大量修订标注数据，而这类数据在社区中极为稀缺且昂贵。为此，我们提出即插即用的分层参数高效微调框架IR-Tuning，通过梯度范数分布动态选择重要层进行微调，同时冻结冗余层。大量实验表明，IR-Tuning在多种文本修订任务上超越多个分层PEFT基线，实现快速收敛、低显存消耗，并在小规模修订语料上依然有效。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have shown extraordinary success across various text generation tasks; however, their potential for simple yet essential text classification remains underexplored, as LLM pre-training tends to emphasize generation over classification. While LLMs with instruction tuning can transform classification into a generation task, they often struggle to categorize nuanced texts. One such example is text revision, which involves nuanced edits between pairs of texts. Although simply fine-tuning LLMs for revision classification seems plausible, it requires a large amount of revision annotations, which are exceptionally expensive and scarce in the community. To address this issue, we introduce a plug-and-play layer-wise parameter-efficient fine-tuning (PEFT) framework, i.e., IR-Tuning, which fine-tunes a subset of important LLM layers that are dynamically selected based on their gradient norm distribution, while freezing those of redundant layers. Extensive experiments suggest that IR-Tuning surpasses several layer-wise PEFT baselines over diverse text revisions, while achieving fast convergence, low GPU memory consumption, and effectiveness on small revision corpora.
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。