Runjin Chen
@RunjinChen
Followers
502
Following
4
Media
1
Statuses
11
Research Fellow @AnthropicAI | PH.D. student @UTAustin @VITAGroupUT | Previously BS/MS @sjtu1896
Joined August 2023
New Anthropic Research: Persona Vectors. We can:.1. Monitor how a model’s personality is changing during a conversation, or over training.2. Mitigate undesirable persona shifts during development or prevent during training. 3. Identify training data that leads to shift.
New Anthropic research: Persona vectors. Language models sometimes go haywire and slip into weird and unsettling personas. Why? In a new paper, we find “persona vectors"—neural activity patterns controlling traits like evil, sycophancy, or hallucination.
8
24
221
RT @EthanJPerez: We’re hiring someone to run the Anthropic Fellows Program!. Our research collaborations have led to some of our best safet….
0
27
0
RT @mlpowered: In which the gang (@RunjinChen, @andyarditi, @Jack_W_Lindsey ):. - identifies vectors for bad personas (evil, sycophancy, ha….
0
9
0
RT @AnthropicAI: New Anthropic research: Persona vectors. Language models sometimes go haywire and slip into weird and unsettling personas….
0
939
0
RT @VictorKaiWang1: Customizing Your LLMs in seconds using prompts🥳!.Excited to share our latest work with @HPCAILab, @VITAGroupUT, @k_schu….
0
75
0
Our LLaGA excels in versatility, generalizability and interpretability, allowing it to perform consistently well across different datasets and tasks, extend its ability to unseen datasets or tasks, and provide explanations for graphs.
0
0
1
Key Feature: A versatile linear projector seamlessly bridges graph structures with the token space understood by Large Language Models (LLMs).
1
0
1
Thrilled to share our latest project, "LLaGA: Large Language and Graph Assistant".🚀 Dive into our findings here: Plus, access our code on GitHub:
1
1
11