Tweak description of TruthfulQA in About

#599
by lewtun HF staff - opened
Files changed (1) hide show
  1. src/display/about.py +1 -1
src/display/about.py CHANGED
@@ -24,7 +24,7 @@ With the plethora of large language models (LLMs) and chatbots being released we
24
  - <a href="https://arxiv.org/abs/1803.05457" target="_blank"> AI2 Reasoning Challenge </a> (25-shot) - a set of grade-school science questions.
25
  - <a href="https://arxiv.org/abs/1905.07830" target="_blank"> HellaSwag </a> (10-shot) - a test of commonsense inference, which is easy for humans (~95%) but challenging for SOTA models.
26
  - <a href="https://arxiv.org/abs/2009.03300" target="_blank"> MMLU </a> (5-shot) - a test to measure a text model's multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more.
27
- - <a href="https://arxiv.org/abs/2109.07958" target="_blank"> TruthfulQA </a> (0-shot) - a test to measure a model's propensity to reproduce falsehoods commonly found online. Note: TruthfulQA in the Harness is actually a minima a 6-shots task, as it is prepended by 6 examples systematically, even when launched using 0 for the number of few-shot examples.
28
  - <a href="https://arxiv.org/abs/1907.10641" target="_blank"> Winogrande </a> (5-shot) - an adversarial and difficult Winograd benchmark at scale, for commonsense reasoning.
29
  - <a href="https://arxiv.org/abs/2110.14168" target="_blank"> GSM8k </a> (5-shot) - diverse grade school math word problems to measure a model's ability to solve multi-step mathematical reasoning problems.
30
 
 
24
  - <a href="https://arxiv.org/abs/1803.05457" target="_blank"> AI2 Reasoning Challenge </a> (25-shot) - a set of grade-school science questions.
25
  - <a href="https://arxiv.org/abs/1905.07830" target="_blank"> HellaSwag </a> (10-shot) - a test of commonsense inference, which is easy for humans (~95%) but challenging for SOTA models.
26
  - <a href="https://arxiv.org/abs/2009.03300" target="_blank"> MMLU </a> (5-shot) - a test to measure a text model's multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more.
27
+ - <a href="https://arxiv.org/abs/2109.07958" target="_blank"> TruthfulQA </a> (0-shot) - a test to measure a model's propensity to reproduce falsehoods commonly found online. Note: TruthfulQA is technically a 6-shot task in the Harness because each example is prepended with 6 Q/A pairs, even in the 0-shot setting.
28
  - <a href="https://arxiv.org/abs/1907.10641" target="_blank"> Winogrande </a> (5-shot) - an adversarial and difficult Winograd benchmark at scale, for commonsense reasoning.
29
  - <a href="https://arxiv.org/abs/2110.14168" target="_blank"> GSM8k </a> (5-shot) - diverse grade school math word problems to measure a model's ability to solve multi-step mathematical reasoning problems.
30