List your company

Harmlessness evaluation on Beavertails

58.4Helpful ScoreAligner
0.88815.81930.7545.681Feb 4, 2024

Evaluation results

MethodLinks
AlignerAligner size=7B, Upstream LLM=Claude 2, Zero-shot=true2024.0258.430.3
AlignerAligner size=7B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.025155.9
AlignerAligner size=13B, Upstream LLM=Claude 2, Zero-shot=true2024.025030
AlignerAligner size=2B, Upstream LLM=Claude 2, Zero-shot=true2024.0238.315.1
AlignerAligner size=7B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.0237.616.6
AlignerAligner size=7B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.0234.947
AlignerAligner size=13B, Upstream LLM=GPT-4, Zero-shot=true2024.0233.925.1
AlignerAligner size=13B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.0233.363.3
AlignerAligner size=13B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.0231.826.7
AlignerAligner size=7B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.0226.415.9
AlignerAligner size=2B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.0225.47.2
AlignerAligner size=2B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.0224.452.4
AlignerAligner size=7B, Upstream LLM=Beaver-7B, Zero-shot=true2024.0221.912
AlignerAligner size=7B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.0220.110.3
AlignerAligner size=7B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.0219.97.4
AlignerAligner size=2B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.0219.414.9
AlignerAligner size=13B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.0219.124
AlignerAligner size=7B, Upstream LLM=GPT-4, Zero-shot=true2024.0218.625.8
AlignerAligner size=2B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.0218.412.3
AlignerAligner size=2B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.0217.85.5
AlignerAligner size=2B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.0216.915.8
AlignerAligner size=13B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.0216.710.6
AlignerAligner size=13B, Upstream LLM=GPT-3.5, Zero-shot=true2024.0215.110.9
AlignerAligner size=13B, Upstream LLM=Beaver-7B, Zero-shot=true2024.0214.219.1
AlignerAligner size=13B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.0213.54.6
AlignerAligner size=13B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.0210.61.9
AlignerAligner size=2B, Upstream LLM=Beaver-7B, Zero-shot=true2024.029.912.1
AlignerAligner size=7B, Upstream LLM=GPT-3.5, Zero-shot=true2024.029.39.3
AlignerAligner size=13B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.028.553.4
AlignerAligner size=2B, Upstream LLM=GPT-4, Zero-shot=true2024.02828.6
AlignerAligner size=2B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.025.845
AlignerAligner size=7B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.025.22.4
AlignerAligner size=2B, Upstream LLM=GPT-3.5, Zero-shot=true2024.023.17.6