[2510.10223] You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs

Computer Science > Computation and Language arXiv:2510.10223 (cs) [Submitted on 11 Oct 2025 (v1), last revised 25 Mar 2026 (this version, v2)] Title:You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs Authors:Yijie Xu, Huizai Yao, Zhiyu Guo, Pengteng Li, Aiwei Liu, Xuming Hu, Weiyu Guo, Hui Xiong View a PDF of the paper titled You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs, by Yijie Xu and 7 other authors View PDF HTML (experimental) Abstract: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 Q...