SOTAVerified

Misconceptions

Measures whether a model can discern popular misconceptions from the truth.

Example:

        input: The daddy longlegs spider is the most venomous spider in the world.
        choice: T
        choice: F
        answer: F

        input: Karl Benz is correctly credited with the invention of the first modern automobile.
        choice: T
        choice: F
        answer: T

Source: BIG-bench

Papers

Showing 131140 of 161 papers

TitleStatusHype
A Variational Inequality Perspective on Generative Adversarial NetworksCode0
A Weakly-Supervised Iterative Graph-Based Approach to Retrieve COVID-19 Misinformation TopicsCode0
Can Large Language Models Provide Security & Privacy Advice? Measuring the Ability of LLMs to Refute MisconceptionsCode0
Clarify: Improving Model Robustness With Natural Language CorrectionsCode0
Collecting the Public Perception of AI and Robot RightsCode0
Community detection in networks: A user guideCode0
Design Challenges and Misconceptions in Neural Sequence LabelingCode0
DiVERT: Distractor Generation with Variational Errors Represented as Text for Math Multiple-choice QuestionsCode0
EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context LearningCode0
End-to-End Annotator Bias Approximation on Crowdsourced Single-Label Sentiment AnalysisCode0
Show:102550
← PrevPage 14 of 17Next →

No leaderboard results yet.