List your company

Harmlessness evaluation on HarmfulQA

69.4Helpfulness ScoreAligner
-9.6410.8831.451.92Feb 4, 2024

Evaluation results

MethodLinks
AlignerAligner size=7B, Upstream LLM=Claude 2, Zero-shot=true2024.0269.442.1
AlignerAligner size=2B, Upstream LLM=Claude 2, Zero-shot=true2024.024814.4
AlignerAligner size=13B, Upstream LLM=Claude 2, Zero-shot=true2024.0245.928.6
AlignerAligner size=7B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.0238.270.7
AlignerAligner size=13B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.0230.918.9
AlignerAligner size=13B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.0230.735
AlignerAligner size=2B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.0226.932.6
AlignerAligner size=13B, Upstream LLM=GPT-4, Zero-shot=true2024.0225.120.1
AlignerAligner size=2B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.0222.665.3
AlignerAligner size=7B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.0221.918.9
AlignerAligner size=2B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.0221.37.2
AlignerAligner size=13B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.0219.531
AlignerAligner size=2B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.0218.627.6
AlignerAligner size=2B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.0217.727.1
AlignerAligner size=2B, Upstream LLM=Vicuna-13B, Zero-shot=true2024.0217.116.1
AlignerAligner size=7B, Upstream LLM=GPT-4, Zero-shot=true2024.0216.328
AlignerAligner size=7B, Upstream LLM=Llama2-13B-Chat, Zero-shot=true2024.0215.528.6
AlignerAligner size=13B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.0212.632.3
AlignerAligner size=2B, Upstream LLM=GPT-4, Zero-shot=true2024.0212.529.2
AlignerAligner size=7B, Upstream LLM=Vicuna-7B, Zero-shot=true2024.021229.3
AlignerAligner size=2B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.0211.325.9
AlignerAligner size=7B, Upstream LLM=Beaver-7B, Zero-shot=true2024.028.96
AlignerAligner size=7B, Upstream LLM=GPT-3.5, Zero-shot=true2024.028.47
AlignerAligner size=13B, Upstream LLM=Beaver-7B, Zero-shot=true2024.02811.6
AlignerAligner size=2B, Upstream LLM=Beaver-7B, Zero-shot=true2024.027.87.6
AlignerAligner size=13B, Upstream LLM=GPT-3.5, Zero-shot=true2024.027.67.7
AlignerAligner size=13B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.027.333.3
AlignerAligner size=13B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.026.37.6
AlignerAligner size=2B, Upstream LLM=GPT-3.5, Zero-shot=true2024.023.64.4
AlignerAligner size=13B, Upstream LLM=Alpaca-7B, Zero-shot=true2024.023.475.9
AlignerAligner size=7B, Upstream LLM=Vicuna-33B, Zero-shot=true2024.02-133.6
AlignerAligner size=7B, Upstream LLM=Llama2-7B-Chat, Zero-shot=true2024.02-5.722.1
AlignerAligner size=7B, Upstream LLM=Llama2-70B-Chat, Zero-shot=true2024.02-6.64.1