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 6170 of 161 papers

TitleStatusHype
The pitfalls of next-token predictionCode2
WatChat: Explaining perplexing programs by debugging mental modelsCode0
Improving the Validity of Automatically Generated Feedback via Reinforcement LearningCode1
The Essential Role of Causality in Foundation World Models for Embodied AI0
Clarify: Improving Model Robustness With Natural Language CorrectionsCode0
Enhancing Diagnostic Accuracy through Multi-Agent Conversations: Using Large Language Models to Mitigate Cognitive Bias0
Distortions in Judged Spatial Relations in Large Language Models0
Finnish 5th and 6th graders' misconceptions about Artificial Intelligence0
Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review0
Fine-tuning Language Models for Factuality0
Show:102550
← PrevPage 7 of 17Next →

No leaderboard results yet.