Self-Adapting Language Models: Paper Authors Discuss Implications
From Deep Papers by Arize AI
July 8, 2025 · 31 min
About this episode
The episode features authors discussing their paper on self-adapting language models and their implications.
The authors of the new paper *Self-Adapting Language Models (SEAL)* shared a behind-the-scenes look at their work, motivations, results, and future directions. The paper introduces a novel method for enabling large language models (LLMs) to adapt their own weights using self-generated data and training directives — “self-edits.” Learn more about the Self-Adapting Language Models paper. Learn more about AI observability and evaluation, join the Arize AI Slack community or get the latest on Lin...
People in this episode
Host: Arize AI
Topics covered
- language models
- self-adaptation
- AI research
- machine learning
- data generation
Keywords
- self-adapting language models
- LLMs
- self-generated data
- training directives
- AI observability
Mentioned in this episode
Organizations: Arize AI
Books & works: Self-Adapting Language Models
More episodes of Deep Papers
- CUGA Agent: From Benchmarks to Business Impact of IBM's Generalist Agent · February 11, 2026 · 23 min
- TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture · November 24, 2025 · 24 min
- Meta AI Researcher Explains ARE and Gaia2: Scaling Up Agent Environments and Evaluations · November 10, 2025 · 23 min
- Georgia Tech's Santosh Vempala Explains Why Language Models Hallucinate, His Research With OpenAI · October 14, 2025 · 31 min
- Atropos Health’s Arjun Mukerji, PhD, Explains RWESummary: A Framework and Test for Choosing LLMs to Summarize Real-World Evidence (RWE) Studies · September 22, 2025 · 26 min
- Stan Miasnikov, Distinguished Engineer, AI/ML Architecture, Consumer Experience at Verizon Walks Us Through His New Paper · September 6, 2025 · 48 min
Explore listener stats, chart rankings, contacts and more on the Deep Papers podcast page.