Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
Paper
•
2304.03279
•
Published
•
2
hlzhang109
hlzhang109
AI & ML interests
None yet
Recent Activity
liked
a model
7 days ago
physical-intelligence/fast
liked
a model
14 days ago
LLM360/K2-Think
commented on
a paper
3 months ago
Discovering Hierarchical Latent Capabilities of Language Models via
Causal Representation Learning
Organizations
authored
5
papers
10 months ago
CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training
Paper
•
2406.10670
•
Published
•
4
DataComp-LM: In search of the next generation of training sets for language models
Paper
•
2406.11794
•
Published
•
54
Eliminating Position Bias of Language Models: A Mechanistic Approach
Paper
•
2407.01100
•
Published
•
9
Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
Paper
•
2412.02674
•
Published