Search Results for author:
Found 10 papers, 6 papers with code
Unleashing the Potential of Large Language Models as Prompt Optimizers: An Analogical Analysis with Gradient-based Model Optimizers
Focused on the two aspects, we borrow the theoretical framework and learning methods from gradient-based optimization to design improved strategies for LLM-based prompt optimizers.
Private Fine-tuning of Large Language Models with Zeroth-order Optimization
We introduce DP-ZO, a new method for fine-tuning large language models that preserves the privacy of training data by privatizing zeroth-order optimization.
Price of Stability in Quality-Aware Federated Learning
The presence of label noise can severely degrade the FL performance, and some existing studies have focused on algorithm design for label denoising.
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Our results demonstrate that our algorithm can achieve competitive performance with strong privacy levels.
Improving Conversational Recommendation Systems via Counterfactual Data Simulation
To develop our approach, we characterize user preference and organize the conversation flow by the entities involved in the dialogue, and design a multi-stage recommendation dialogue simulator based on a conversation flow language model.
Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs), which rely on natural language conversations to satisfy user needs.
A Survey of Large Language Models
To discriminate the difference in parameter scale, the research community has coined the term large language models (LLM) for the PLMs of significant size.
DP-RAFT: A Differentially Private Recipe for Accelerated Fine-Tuning
A major direction in differentially private machine learning is differentially private fine-tuning: pretraining a model on a source of "public data" and transferring the extracted features to downstream tasks.
Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
The goal of this work is to train ML models that have high membership privacy while largely preserving their utility; we therefore aim for an empirical membership privacy guarantee as opposed to the provable privacy guarantees provided by techniques like differential privacy, as such techniques are shown to deteriorate model utility.
Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning
This paper addresses a new problem of understanding human gaze communication in social videos from both atomic-level and event-level, which is significant for studying human social interactions.
