Common Sense Reasoning
259 papers with code • 24 benchmarks • 52 datasets
Common sense reasoning tasks are intended to require the model to go beyond pattern recognition. Instead, the model should use "common sense" or world knowledge to make inferences.
Benchmarks
These leaderboards are used to track progress in Common Sense Reasoning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Common Sense Reasoning models and implementationsDatasets
WinoGrande
CommonsenseQA
BIG-bench
VisDial
SWAG
ReCoRD
ARC (AI2 Reasoning Challenge)
CoS-E
PHYRE
Subtasks
Latest papers
A Content-Based Novelty Measure for Scholarly Publications: A Proof of Concept
Novelty, akin to gene mutation in evolution, opens possibilities for scholarly advancement.
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
wuhy68/parameter-efficient-moe
•
•
Instruction tuning, a successful paradigm, enhances the ability of LLMs to follow natural language instructions and exhibit robust generalization across a wide range of tasks.
Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference
p1nksnow/MSIC
•
•
Furthermore, we propose to generate medical reports to add textual descriptions for each medical event, providing broader applications for synthesized EHR data.
A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties
lambert-x/prolab
•
•
Instead of relying solely on category-specific annotations, ProLab uses descriptive properties grounded in common sense knowledge for supervising segmentation models.
CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models
With these pre-defined domains and slots, we collect 76, 787 commonsense knowledge annotations from 19, 700 dialogues through crowdsourcing.
Holodeck: Language Guided Generation of 3D Embodied AI Environments
allenai/Holodeck
•
•
3D simulated environments play a critical role in Embodied AI, but their creation requires expertise and extensive manual effort, restricting their diversity and scope.
Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia
Agent-based modeling has been around for decades, and applied widely across the social and natural sciences.
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.
Speak Like a Native: Prompting Large Language Models in a Native Style
Specifically, with AlignedCoT, we observe an average +3. 2\% improvement for \texttt{gpt-3. 5-turbo} compared to the carefully handcrafted CoT on multi-step reasoning benchmarks. Furthermore, we use AlignedCoT to rewrite the CoT text style in the training set, which improves the performance of Retrieval Augmented Generation by 3. 6\%. The source code and dataset is available at https://github. com/yangzhch6/AlignedCoT
A Language Agent for Autonomous Driving
Our approach, termed Agent-Driver, transforms the traditional autonomous driving pipeline by introducing a versatile tool library accessible via function calls, a cognitive memory of common sense and experiential knowledge for decision-making, and a reasoning engine capable of chain-of-thought reasoning, task planning, motion planning, and self-reflection.
