
PaLM paper: Word in Context benchmark (PaLM 540B) Patel & Pavlick: grounded conceptual mappings (GPT-3 175B) Gopher paper: Toxicity classification (Gopher 7.1B), TruthfulQA (Gopher 280B) GPT-3 paper: 3 digit addition/subtraction (GPT-3 13B), 4-5 digit addition/substraction (GPT-3 175B), leveraging few-shot examples for word denoising (GPT-3 13B) In addition to these large repositories of tasks, several papers have also shown individual tasks as emergent abilities:
#Phenomena movie languages professional
#Phenomena movie languages movie
PaLM 540B (25 tasks): analogical similarity, causal judgment, code line description, crass ai, cs algorithms, elementary math qa, english russian proverbs, geometric shapes, hyperbaton, identify odd metaphor, international phonetic alphabet nli, language identification, logical fallacy detection, logical sequence, movie dialog same or different, physics questions, question selection, temporal sequences, understanding fables, unit interpretation, snarks, english proverbs, timedial, hinglish toxicity, vitaminc fact verification.PaLM 64B (14 tasks): anachronisms, ascii word recognition, conceptual combinations, cryptonite, disambiguation qa, emoji movie, goal step wikihow, gre reading comprehension, linguistics puzzles, logic grid puzzle, metaphor understanding, odd one out, metaphor boolean, parsinlu qa.PaLM 8B (3 tasks): auto debugging, sufficient information, parsinlu reading comprehension.

LaMDA 137B (8 tasks): gender inclusive sentences german, repeat copy logic, sports understanding, swahili english proverbs, word sorting, word unscrambling, irony identification, logical args.GPT-3 175B (15 tasks): analytic entailment, codenames, phrase relatedness, question answer creation, self evaluation tutoring, common morpheme, fact checker, figure of speech detection, international phonetic alphabet transliterate, logical deduction, misconceptions, physical intuition, social iqa, strange stories, strategyqa.GPT-3 13B (2 tasks): hindu knowledge, modified arithmetic.
