Chujie Zheng

chujiezheng's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 23 days ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published 24 days ago • 161

authored 3 papers about 1 month ago

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs

Paper • 2505.13529 • Published May 18 • 11

Qwen3 Technical Report

Paper • 2505.09388 • Published May 14 • 203

WorldPM: Scaling Human Preference Modeling

Paper • 2505.10527 • Published May 15 • 33

authored 2 papers 4 months ago

Aligning Instruction Tuning with Pre-training

Paper • 2501.09368 • Published Jan 16

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published Feb 20 • 104

authored a paper 5 months ago

The Lessons of Developing Process Reward Models in Mathematical Reasoning

Paper • 2501.07301 • Published Jan 13 • 99

authored 2 papers 7 months ago

ProcessBench: Identifying Process Errors in Mathematical Reasoning

Paper • 2412.06559 • Published Dec 9, 2024 • 84

Yi-Lightning Technical Report

Paper • 2412.01253 • Published Dec 2, 2024 • 29

authored 2 papers 12 months ago

Weak-to-Strong Extrapolation Expedites Alignment

Paper • 2404.16792 • Published Apr 25, 2024 • 11

Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks

Paper • 2407.02855 • Published Jul 3, 2024 • 13

authored a paper over 1 year ago

Prompt-Driven LLM Safeguarding via Directed Representation Optimization

Paper • 2401.18018 • Published Jan 31, 2024 • 1

authored 5 papers almost 2 years ago

CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation

Paper • 2208.08845 • Published Aug 18, 2022

CEM: Commonsense-aware Empathetic Response Generation

Paper • 2109.05739 • Published Sep 13, 2021

PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support

Paper • 2106.01702 • Published Jun 3, 2021

On Large Language Models' Selection Bias in Multi-Choice Questions

Paper • 2309.03882 • Published Sep 7, 2023

Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation

Paper • 2109.06513 • Published Sep 14, 2021

authored 3 papers about 2 years ago

Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning

Paper • 2306.03350 • Published Jun 6, 2023

EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training

Paper • 2108.01547 • Published Aug 3, 2021

EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training

Paper • 2203.09313 • Published Mar 17, 2022