仅用4个额外标记，让大模型实时适应新领域。
You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs
- 结合输入困惑度与输出熵，动态检测分布偏移。
- 农业问答任务中，性能提升超120%。
- 无需标注数据，适合标签稀缺场景。
大语言模型在金融、医疗、农业等专业领域部署时，常面临训练数据与实际应用间分布差异的问题。领域特定微调虽能缓解此问题，但依赖高质量标注数据，而这类数据在专业性受限的场景中获取成本高、速度慢。本文研究无监督的测试时自适应方法，提出SyTTA框架，在推理阶段无需额外监督即可实时调整模型。SyTTA融合两种互补的不确定性信号：输入侧的困惑度反映与领域术语和模式的不匹配；输出侧的预测熵反映生成过程中的概率模糊与不稳定。在多种模型架构与领域基准上，SyTTA均表现稳定且显著提升。尤其在农业问答任务中，使用Qwen-2.5-7B模型，每查询仅增加4个额外标记，便使Rouge-LSum指标提升超过120%。结果表明，无需标注样本即可实现高效测试时自适应，支持模型在标签稀缺领域的部署。代码将在论文接受后公开。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly deployed in specialized domains such as finance, medicine, and agriculture, where they face significant distribution shifts from their training data. Domain-specific fine-tuning can mitigate this challenge but relies on high-quality labeled data that is expensive and slow to collect in expertise-limited settings. We study label-free test-time adaptation for language models and present SyTTA, an inference-time framework that adapts models on-the-fly without additional supervision. SyTTA couples two complementary uncertainty signals that arise under distribution shift: input-side perplexity, indicating mismatch with domain-specific terminology and patterns, and output-side predictive entropy, indicating diffuse and unstable token probabilities during generation. Across diverse model architectures and domain-specific benchmarks, SyTTA delivers consistent gains. Notably, on agricultural question answering, SyTTA improves Rouge-LSum by over 120% on Qwen-2.5-7B with only 4 extra tokens per query. These results show that effective test-time adaptation for language models is achievable without labeled examples, supporting deployment in label-scarce domains. The code will be made available upon acceptance.
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。