Natural Language Processing (NLP)

2 Posts

Diagram showing GPT-4o with and without search, highlighting task execution success and failure.
Natural Language Processing (NLP)

Tree Search for Web Agents: How tree search improves AI agents’ ability to browse the web and complete tasks

Browsing the web to achieve a specific goal can be challenging for agents based on large language models and even for vision-language models that can process onscreen images of a browser.
Bar chart comparing active vs. random sampling effects on length, diversity, and toxicity after fine-tuning.
Natural Language Processing (NLP)

Fine-Tuning Fine Points: Active inheritance, a smarter way to fine-tune models on synthetic data

The practice of fine-tuning models on synthetic data is becoming well established. But synthetic training data, even if it represents the training task well, may include characteristics like toxicity that impart unwelcome properties in the trained model’s output...

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox