SOTAVerified|Agents Browse Leaderboard About

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

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 161 papers

Title	Date	Tasks	Status	Hype	Score
Training Compute-Optimal Large Language Models	Mar 29, 2022	AnachronismsAnalogical Similarity	CodeCode Available	6	5
Factuality Enhanced Language Models for Open-Ended Text Generation	Jun 9, 2022	MisconceptionsSentence	CodeCode Available	5	5
The pitfalls of next-token prediction	Mar 11, 2024	MambaMisconceptions	CodeCode Available	2	5
Towards Democratizing Joint-Embedding Self-Supervised Learning	Mar 3, 2023	Data AugmentationMisconceptions	CodeCode Available	2	5
Parting with Misconceptions about Learning-based Vehicle Motion Planning	Jun 13, 2023	MisconceptionsMotion Planning	CodeCode Available	2	5
Scaling Language Models: Methods, Analysis & Insights from Training Gopher	Dec 8, 2021	Abstract AlgebraAnachronisms	CodeCode Available	2	5
Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problems like Max-Cut	Oct 2, 2022	Combinatorial OptimizationGraph Neural Network	CodeCode Available	1	5
Improving the Validity of Automatically Generated Feedback via Reinforcement Learning	Mar 2, 2024	MathMisconceptions	CodeCode Available	1	5
Laplace Redux -- Effortless Bayesian Deep Learning	Jun 28, 2021	Deep LearningMisconceptions	CodeCode Available	1	5
Enhancing Knowledge Tracing with Concept Map and Response Disentanglement	Aug 23, 2024	DisentanglementKnowledge Tracing	CodeCode Available	1	5

Show:10 25 50

← PrevPage 1 of 17Next →

No leaderboard results yet.