I’ve got the “Answer”! Interpretation of LLMs Hidden States in Question Answeringby Valeriya Goloviznina, Evgeny…
Annotation Guidelines-Based Knowledge Augmentation: Towards Enhancing Large Language Models for Educational Text Classificationby Shiqi Liu,…
A Theory for Token-Level Harmonization in Retrieval-Augmented Generationby Shicheng Xu, Liang Pang, Huawei Shen, Xueqi…
FOCUS: Forging Originality through Contrastive Use in Self-Plagiarism for Language Modelsby Kaixin Lan, Tao Fang,…
Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categoriesby Tianlong Wang,…
Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingby Feiteng Fang, Yuelin Bai,…
Hidden in Plain Sight: Exploring Chat History Tampering in Interactive Language Modelsby Cheng'an Wei, Yue…
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projectionsby Roy Miles, Pradyumna Reddy, Ismail Elezi, Jiankang…
Proof of Quality: A Costless Paradigm for Trustless Generative AI Model Inference on Blockchainsby Zhenjie…
Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenizationby Dixuan Wang, Yanda Li, Junyuan…