Picture for Wenhong Zhu

Wenhong Zhu

Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model

Add code
Oct 24, 2024
Viaarxiv icon

Improving Open-Ended Text Generation via Adaptive Decoding

Add code
Feb 28, 2024
Viaarxiv icon

Is Cognition and Action Consistent or Not: Investigating Large Language Model's Personality

Add code
Feb 22, 2024
Viaarxiv icon

CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models

Add code
Nov 15, 2023
Viaarxiv icon

Penalty Decoding: Well Suppress the Self-Reinforcement Effect in Open-Ended Text Generation

Add code
Oct 23, 2023
Viaarxiv icon