LLM Unlearning Benchmarks are Weak Measures of Progress – Machine Learning Blog | ML@CMU
TL;DR: “Machine unlearning” aims to remove data from models without retraining the model completely. Unfortunately, state-of-the-art ...
Read moreTag: LLM
Mastering Your Own LLM: A Step-by-Step Guide
Mastering Your Own LLM: A Step-by-Step GuideMastering Your Own LLM: A Step-by-Step Guide is your ultimate ...
Read more
Ethical Considerations and Best Practices in LLM Development
Bias is inherent to building a ML model. Bias exists on a spectrum. Our job is ...
Read more
SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
Large Language Models (LLMs) have transformed natural language processing, but face significant challenges in widespread deployment ...
Read moreToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
Recent large language models (LLMs) advancements sparked a growing research interest in tool assisted LLMs solving ...
Read more
How to Build an LLM Agent With AutoGen: Step-by-Step Guide
LLM agents extend the capabilities of pre-trained language models by integrating tools like Retrieval-Augmented Generation (RAG), ...
Read more
Optimizing LLM Test-Time Compute Involves Solving a Meta-RL Problem – Machine Learning Blog | ML@CMU
Figure 1: Training models to optimize test-time compute and learn “how to discover” correct responses, as ...
Read more