J Li

jiazhengli's activity

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

upvoted a paper 23 days ago

Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time

Paper • 2502.19230 • Published Feb 26 • 1

upvoted a collection 28 days ago

RoleMRC

Collection

A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following • 6 items • Updated Mar 7 • 1

upvoted a paper 2 months ago

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models

Paper • 2501.13629 • Published Jan 23 • 48

upvoted 2 papers 6 months ago

Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence

Paper • 2406.10957 • Published Jun 16, 2024 • 1

Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring

Paper • 2406.19949 • Published Jun 28, 2024 • 1

upvoted 3 collections 6 months ago

AERA

Collection

Resources for EMNLP 2023 Paper: Distilling ChatGPT for Explainable Automated Student Answer Assessment • 3 items • Updated Oct 14, 2024 • 1

MCTS with Preference Optimisation

Collection

Resources for EMNLP 2024 Paper: Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring • 8 items • Updated Oct 14, 2024 • 2

SamPO

Collection

Resources for EMNLP 2024 Paper: Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence • 4 items • Updated Oct 14, 2024 • 2