Large language models (LLMs) demonstrate strong reasoning capabilities, but their performance often degrades under distribution shift. Existing test-time adaptation (TTA) methods rely on gradient-based updates that require white-box access and need substantial overhead, while training-free alternatives are either static or depend on external guidance. In this paper, we propose Training-Free Test-Time Contrastive Learning TF-TTCL, a training-free adaptation framework that enables a frozen LLM to improve online by distilling supervision from its own inference experiences. Specifically, TF-TTCL implements a dynamic "Explore-Reflect-Steer" loop through three core modules: 1) Semantic Query Augmentation first diversifies problem views via multi-agent role-playing to generate different reasoning trajectories; 2) Contrastive Experience Distillation then captures the semantic gap between superior and inferior trajectories, distilling them into explicit textual rules; and 3) Contextual Rule Retrieval finally activates these stored rules during inference to dynamically steer the frozen LLM toward robust reasoning patterns while avoiding observed errors. Extensive experiments on closed-ended reasoning tasks and open-ended evaluation tasks demonstrate that TF-TTCL consistently outperforms strong zero-shot baselines and representative TTA methods under online evaluation. Code is available at https://github.com/KevinSCUTer/TF-TTCL.
A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement
Department of Electrical and Computer Engineering, McGill University(麦吉尔大学电气与计算机工程系);Department of Mechanical, Industrial and Aerospace Engineering, Concordia University(Concordia大学机械、工业与航空航天工程系)
Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
Nanyang Technological University(南洋理工大学);Carnegie Mellon University(卡内基梅隆大学);University of California, Santa Barbara(加州大学圣巴巴拉分校);National University Singapore(新加坡国立大学)
Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents
University of Michigan(密歇根大学);AWS AI Labs(亚马逊云科技人工智能实验室)
我们研究了半结构化文档分类在一个zero-shot设置。半结构化文档的分类比标准的非结构化文档更具挑战性,因为位置、布局和样式信息在解释此类文档时起着至关重要的作用。在训练和测试期间类别都是固定的标准分类设置在可能出现新文档类别的动态环境中是不够的。我们专注于专门的zero-shot设置,其中的推理是在新的看不见的类。为了解决这个问题,我们提出了一种基于匹配的方法,它依赖于一个成对的对比目标进行预训练和微调。我们的研究结果表明,在监督和无监督zero-shot设置中,Macro F $_1$从建议的预训练步骤中得到了显着的提升。
TQ-Net: Mixed Contrastive Representation Learning For Heterogeneous Test Questions
Brainnetome Center, National Laboratory of Pattern Recognition (NLPR), CASIA(脑网络组中心,模式识别国家重点实验室,中国科学院自动化研究所);Tencent Inc. China(腾讯公司(中国));School of Future Technology, University of Chinese Academy of Sciences (UCAS)(中国科学院大学未来技术学院)
Steering Speech-Language Models: Training-Free Task Specialization via Contrastive Activation Addition
Univ Toulon, Aix Marseille Univ, LIS, CNRS(土伦大学,艾克斯-马赛大学,LIS,法国国家科学研究中心);Mila – Quebec AI Institute(Mila – 魁北克人工智能研究所);Idiap Research Institute(Idiap 研究所);Sapienza University of Rome(罗马大学);Brno University of Technology(布尔诺理工大学);pyannoteAI(pyannoteAI 公司);Concordia University(康考迪亚大学);CNRS, ILLS(法国国家科学研究中心,ILLS)
Selective Contrastive Learning For Gloss Free Sign Language Translation
School of Informatics, Xiamen University, China(厦门大学信息学院);Key Lab of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian-Taiwan (XMU), Ministry of Culture and Tourism, China(福建省 Fujian-Taiwan 非物质文化遗产数字保护与智能处理重点实验室,文化部,中国);National Language Resources Monitoring and Research Center for Education and Teaching Media, Xiamen University, China(教育与教学媒体语言资源监测与研究中心,厦门大学,中国)
CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks
University of Mannheim(曼海姆大学);University of Technology Nuremberg(纽伦堡技术大学);Max Planck Institute for Informatics, Saarland Informatics Campus(马克斯·普朗克信息研究所,萨尔兰信息校园)