SOTAVerified

Common Sense Reasoning

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.

Papers

Showing 651700 of 939 papers

TitleStatusHype
Let's Think Var-by-Var: Large Language Models Enable Ad Hoc Probabilistic Reasoning0
Leveraging Large Language Model-based Room-Object Relationships Knowledge for Enhancing Multimodal-Input Object Goal Navigation0
Leveraging Large Language Models in Conversational Recommender Systems0
Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection0
Linguistic Embeddings as a Common-Sense Knowledge Repository: Challenges and Opportunities0
LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following0
LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning0
LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decomposition0
LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions0
LLM-enhanced Scene Graph Learning for Household Rearrangement0
LLMs for Relational Reasoning: How Far are We?0
LMPriors: Pre-Trained Language Models as Task-Specific Priors0
LMVE at SemEval-2020 Task 4: Commonsense Validation and Explanation using Pretraining Language Model0
LogicalDefender: Discovering, Extracting, and Utilizing Common-Sense Knowledge0
LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehension0
Machine Common Sense0
Machine Common Sense Concept Paper0
Machine Reasoning: Technology, Dilemma and Future0
MACI: Multi-Agent Collaborative Intelligence for Adaptive Reasoning and Temporal Planning0
MALT: Improving Reasoning with Multi-Agent LLM Training0
Mandarinograd: A Chinese Collection of Winograd Schemas0
ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation0
Markov Chains for Robust Graph-Based Commonsense Information Extraction0
Mathematics, word problems, common sense, and artificial intelligence0
mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans0
Measuring an Artificial Intelligence System's Performance on a Verbal IQ Test For Young Children0
Measuring Numerical Common Sense: Is A Word Embedding Approach Effective?0
Median DC for Sign Recovery: Privacy can be Achieved by Deterministic Algorithms0
MERALI at SemEval-2017 Task 2 Subtask 1: a Cognitively Inspired approach0
Meta-Control: Automatic Model-based Control Synthesis for Heterogeneous Robot Skills0
Mind meets machine: Unravelling GPT-4's cognitive psychology0
Minimally Naturalistic Artificial Intelligence0
Mise en Place: Unsupervised Interpretation of Instructional Recipes0
MIT-MEDG at SemEval-2018 Task 7: Semantic Relation Classification via Convolution Neural Network0
MITRE at SemEval-2018 Task 11: Commonsense Reasoning without Commonsense Knowledge0
Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs0
Model Card and Evaluations for Claude Models0
Modeling and Control of bittide Synchronization0
Modeling Semantic Expectation: Using Script Knowledge for Referent Prediction0
Modeling Semantics and Pragmatics of Spatial Prepositions via Hierarchical Common-Sense Primitives0
Modeling Sentiment Association in Discourse for Humor Recognition0
Modular Approach to Machine Reading Comprehension: Mixture of Task-Aware Experts0
MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models0
Most ``babies'' are ``little'' and most ``problems'' are ``huge'': Compositional Entailment in Adjective-Nouns0
MovieGraphs: Towards Understanding Human-Centric Situations from Videos0
MR-MLLM: Mutual Reinforcement of Multimodal Comprehension and Vision Perception0
MSWA: Refining Local Attention with Multi-ScaleWindow Attention0
Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes0
Multilingual Text Representation0
Multi-modal Cooking Workflow Construction for Food Recipes0
Show:102550
← PrevPage 14 of 19Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ST-MoE-32B 269B (fine-tuned)Accuracy96.1Unverified
2Unicorn 11B (fine-tuned)Accuracy91.3Unverified
3CompassMTL 567M with TailorAccuracy90.5Unverified
4CompassMTL 567MAccuracy89.6Unverified
5UnifiedQA 11B (fine-tuned)Accuracy89.4Unverified
6Claude 3 Opus (5-shot)Accuracy88.5Unverified
7GPT-4 (5-shot)Accuracy87.5Unverified
8ExDeBERTa 567MAccuracy87Unverified
9LLaMA-2 13B + MixLoRAAccuracy86.3Unverified
10LLaMA3 8B+MoSLoRAAccuracy85.8Unverified
#ModelMetricClaimedVerifiedStatus
1GPT-4 (few-shot, k=25)Accuracy96.4Unverified
2PaLM 2 (few-shot, CoT, SC)Accuracy95.1Unverified
3Shivaay (4B, few-shot, k=8)Accuracy91.04Unverified
4StupidLLMAccuracy91.03Unverified
5Claude 2 (few-shot, k=5)Accuracy91Unverified
6Claude 1.3 (few-shot, k=5)Accuracy90Unverified
7PaLM 540B (Self Improvement, Self Consistency)Accuracy89.8Unverified
8PaLM 540B (Self Consistency)Accuracy88.7Unverified
9PaLM 540B (Self Improvement, CoT Prompting)Accuracy88.3Unverified
10PaLM 540B (Self Improvement, Standard-Prompting)Accuracy87.2Unverified
#ModelMetricClaimedVerifiedStatus
1ST-MoE-32B 269B (fine-tuned)Accuracy95.2Unverified
2LLaMA 3 8B+MoSLoRA (fine-tuned)Accuracy90.5Unverified
3PaLM 2-L (1-shot)Accuracy89.7Unverified
4PaLM 2-M (1-shot)Accuracy88Unverified
5LLaMA-3 8B + MixLoRAAccuracy86.5Unverified
6Camelidae-8×34BAccuracy86.2Unverified
7PaLM 2-S (1-shot)Accuracy85.6Unverified
8LLaMA 65B + CFG (0-shot)Accuracy84.2Unverified
9GAL 120B (0-shot)Accuracy83.8Unverified
10LLaMA-2 13B + MixLoRAAccuracy83.5Unverified
#ModelMetricClaimedVerifiedStatus
1Turing NLR v5 XXL 5.4B (fine-tuned)EM95.9Unverified
2ST-MoE-32B 269B (fine-tuned)EM95.1Unverified
3T5-11BF194.1Unverified
4DeBERTa-1.5BEM94.1Unverified
5PaLM 540B (finetuned)EM94Unverified
6Vega v2 6B (fine-tuned)EM93.9Unverified
7PaLM 2-L (one-shot)F193.8Unverified
8T5-XXL 11B (fine-tuned)EM93.4Unverified
9PaLM 2-M (one-shot)F192.4Unverified
10PaLM 2-S (one-shot)F192.1Unverified