Diagnosing and Repairing Persona Collapse in LLM Advice
Collection
LoRA adapters for Olmo-3-7B-Instruct from arXiv:2607.08326. • 5 items • Updated
Harsh Kumar
harsh9
·
AI & ML interests
AI character and behavior training.
Recent Activity
updated a collection 7 days ago
Diagnosing and Repairing Persona Collapse in LLM Advice updated a collection 7 days ago
Diagnosing and Repairing Persona Collapse in LLM Advice updated a collection 7 days ago
Diagnosing and Repairing Persona Collapse in LLM AdviceOrganizations
updated a
collection 7 days ago
published 4
models 7 days ago
harsh9/persona-collapse-ipd-sft-olmo3-7b
Text Generation • Updated • 6
harsh9/persona-collapse-ref-sft-quality-grpo-olmo3-7b
Text Generation • Updated • 18
harsh9/persona-collapse-quality-grpo-olmo3-7b
Text Generation • Updated • 11
harsh9/persona-collapse-ref-sft-olmo3-7b
Text Generation • Updated • 17
updated 4
models 7 days ago
harsh9/persona-collapse-ipd-sft-olmo3-7b
Text Generation • Updated • 6
harsh9/persona-collapse-ref-sft-quality-grpo-olmo3-7b
Text Generation • Updated • 18
harsh9/persona-collapse-quality-grpo-olmo3-7b
Text Generation • Updated • 11
harsh9/persona-collapse-ref-sft-olmo3-7b
Text Generation • Updated • 17
authored 4
papers 13 days ago
Human Creativity in the Age of LLMs: Randomized Experiments on Divergent and Convergent Thinking
Paper • 2410.03703 • Published
Diagnosing and Repairing Persona Collapse in LLM Advice
Paper • 2607.08326 • Published
Position: We Need Large Language Models Optimized For Our Well-Being
Paper • 2608.07505 • Published
Social Priors: Descriptions of AI Users Shape How Language Models Trust and Cooperate
Paper • 2610.16946 • Published
updated a
collection 13 days ago