Salsabila Mahdi
- Steering Without Side Effects: Improving Post-Deployment Control of Language Models
2024/06/21 by Asa Cooper Stickland, Alexander Lyzhov, Stickland, Asa Cooper +7 · 10 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multi-Agent Systems and Negotiation #Natural Language Processing Techniques
- Debate Helps Supervise Unreliable Experts
2023/11/15 by Julian Michael, Salsabila Mahdi, Michael, Julian +11 · 4 citations
Computer Science · #Expert finding and Q&A systems #Topic Modeling #Explainable Artificial Intelligence (XAI)