TrustLLM: Trustworthiness in Large Language Models
Paper
•
2401.05561
•
Published
•
65
Safety / Alignment / Policies / SMI
đź”–Cheatsheet: http://tinyurl.com/35vvs6d9 đź”–Foundation Model Cheatsheet: https://fmcheatsheet.org/
Note đź’«https://deepmind.google/discover/blog/the-ethics-of-advanced-ai-assistants/ https://shorturl.at/w9AmR (210 page book from Google DeepMind!)
-
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Paper • 2303.12712 • Published • 2
Secrets of RLHF in Large Language Models Part II: Reward Modeling
Paper • 2401.06080 • Published • 26Note Refer "Experiment Details" ➡️ Evaluation
-
Measuring Implicit Bias in Explicitly Unbiased Large Language Models
Paper • 2402.04105 • Published • 1 -
Confidence-Building Measures for Artificial Intelligence: Workshop Proceedings
Paper • 2308.00862 • Published -
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
Paper • 2401.12070 • Published • 43 -
Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
Paper • 2305.04388 • Published • 1 -
ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming
Paper • 2404.08676 • Published • 3 -
unalignment/toxic-dpo-v0.2
Viewer • Updated • 541 • 149 • 117 -
unalignment/toxic-dpo-v0.1
Viewer • Updated • 302 • 54 • 132 -
Anthropic/hh-rlhf
Viewer • Updated • 169k • 9.82k • 1.21k -
meta-llama/LlamaGuard-7b
Text Generation • Updated • 7.7k • 216 -
Anthropic/persuasion
Viewer • Updated • 3.94k • 412 • 175