27 citations · 35 across the 5 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.CL2024
Training Language Models to Win Debates with Self-Play Improves Judge Accuracy
Samuel Arnesen, David Rein, Julian Michael
We test the robustness of debate as a method of scalable oversight by training models to debate with data generated via self-play. In a long-context reading comprehension task, we…
cs.CL2024
Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
James Chua, Edward Rees, Hunar Batra +4
Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing m…