Kamal Ndousse

According to our database1, Kamal Ndousse authored at least 19 papers between 2020 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.
CoRR, 2024

Towards Understanding Sycophancy in Language Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Specific versus General Principles for Constitutional AI.
CoRR, 2023

Towards Understanding Sycophancy in Language Models.
CoRR, 2023

The Capacity for Moral Self-Correction in Large Language Models.
CoRR, 2023


2022
Discovering Language Model Behaviors with Model-Written Evaluations.
CoRR, 2022

Constitutional AI: Harmlessness from AI Feedback.
CoRR, 2022

Measuring Progress on Scalable Oversight for Large Language Models.
CoRR, 2022

In-context Learning and Induction Heads.
CoRR, 2022

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.
CoRR, 2022

Language Models (Mostly) Know What They Know.
CoRR, 2022

Evolution through Large Models.
CoRR, 2022

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.
CoRR, 2022

Predictability and Surprise in Large Generative Models.
CoRR, 2022


2021
A General Language Assistant as a Laboratory for Alignment.
CoRR, 2021

Emergent Social Learning via Multi-agent Reinforcement Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021

2020
Multi-agent Social Reinforcement Learning Improves Generalization.
CoRR, 2020


  Loading...