Malikeh Ehghaghi
Malikeh1375
AI & ML interests
NLP, Modular ML, Model Merging, Decentralized Training, Efficient LLMs
Recent Activity
liked
a dataset 5 days ago
google/deepsearchqa updated
a collection
15 days ago
AI Safety Benchmarks updated
a collection
15 days ago
AI Safety Benchmarks Organizations
LLM-Alignment
-
Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
Paper • 2403.09704 • Published • 32 -
Aligners: Decoupling LLMs and Alignment
Paper • 2403.04224 • Published -
LAB: Large-Scale Alignment for ChatBots
Paper • 2403.01081 • Published -
Using Large Language Models for Natural Language Processing Tasks in Requirements Engineering: A Systematic Guideline
Paper • 2402.13823 • Published
Medical Datasets
Clustered Tulu
LLM Interpretability
-
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 23 -
From Understanding to Utilization: A Survey on Explainability for Large Language Models
Paper • 2401.12874 • Published • 4 -
Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
Paper • 2401.13986 • Published
AI Safety Benchmarks
Clustered Tulu
LLM-Alignment
-
Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
Paper • 2403.09704 • Published • 32 -
Aligners: Decoupling LLMs and Alignment
Paper • 2403.04224 • Published -
LAB: Large-Scale Alignment for ChatBots
Paper • 2403.01081 • Published -
Using Large Language Models for Natural Language Processing Tasks in Requirements Engineering: A Systematic Guideline
Paper • 2402.13823 • Published
LLM Interpretability
-
Rethinking Interpretability in the Era of Large Language Models
Paper • 2402.01761 • Published • 23 -
From Understanding to Utilization: A Survey on Explainability for Large Language Models
Paper • 2401.12874 • Published • 4 -
Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
Paper • 2401.13986 • Published
Medical Datasets