T2T LLMs

Text-to-Text (T2T) large language models (LLMs) that power generalized ChatBots, such as ChatGPT, have revolutionized the landscape for how artificial intelligence can be used, both in industry and by individuals. Challenges exist, however, with these systems in areas like trust, safety, factual accuracy, bias mitigation, etc. 

Though not comprehensive, the following list of research and white papers represents the work of hundreds of individuals and organizations that are trying to make AI safer and more trustworthy for us all.

Hazard, Harm and/or Risk Taxonomies

LLM Safety Benchmarks

LLM Capability Benchmarks

LLM Benchmark Aggregation

Assessing AI LLM Benchmarks

Evaluating LLMs