Search Results for author:
Found 8 papers, 2 papers with code
On Large Language Models' Hallucination with Regard to Known Facts
In hallucinated cases, the output token's information rarely demonstrates abrupt increases and consistent superiority in the later stages of the model.
Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning
However, current EM-based methods retrieves memory globally by performing Vector-to-Vector (V2V) interaction between features corresponding to the input and prototypes stored in EM, neglecting the geometric structure of local features.
Interactive Continual Learning: Fast and Slow Thinking
Drawing on Complementary Learning System theory, this paper presents a novel Interactive Continual Learning (ICL) framework, enabled by collaborative interactions among models of various sizes.
CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
With the advancement of language models (LMs), their exposure to private data is increasingly inevitable, and their deployment (especially for smaller ones) on personal devices, such as PCs and smartphones, has become a prevailing trend.
Investigating Deep Watermark Security: An Adversarial Transferability Perspective
The rise of generative neural networks has triggered an increased demand for intellectual property (IP) protection in generated content.
Large Language Models are Zero Shot Hypothesis Proposers
We subsequently evaluate the hypothesis generation capabilities of various top-tier instructed models in zero-shot, few-shot, and fine-tuning settings, including both closed and open-source LLMs.
CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model
Instruction tuning has recently been recognized as an effective way of aligning Large Language Models (LLMs) to enhance their generalization ability across various tasks.
PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning
While large language models (LLMs) excel in various natural language processing tasks, their huge size and the inaccessibility of parameters present challenges for practical deployment.
