Picture for Xiang Ren

Xiang Ren

WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild

Add code
Sep 05, 2024
Viaarxiv icon

Rethinking Backdoor Detection Evaluation for Language Models

Add code
Aug 31, 2024
Viaarxiv icon

Symbolic Working Memory Enhances Language Models for Complex Rule Application

Add code
Aug 24, 2024
Viaarxiv icon

Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack

Add code
Jul 23, 2024
Viaarxiv icon

Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance

Add code
Jul 10, 2024
Viaarxiv icon

CAVE: Controllable Authorship Verification Explanations

Add code
Jun 24, 2024
Viaarxiv icon

Demystifying Forgetting in Language Model Fine-Tuning with Statistical Analysis of Example Associations

Add code
Jun 20, 2024
Viaarxiv icon

WildChat: 1M ChatGPT Interaction Logs in the Wild

Add code
May 02, 2024
Viaarxiv icon

CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting

Add code
Apr 16, 2024
Viaarxiv icon

Logits of API-Protected LLMs Leak Proprietary Information

Add code
Mar 15, 2024
Viaarxiv icon