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 101150 of 939 papers

TitleStatusHype
PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) PlanningCode1
Large Language Models Are Not Strong Abstract ReasonersCode1
ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet CategoriesCode1
ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text GamesCode1
Reasoning Implicit Sentiment with Chain-of-Thought PromptingCode1
AR-Diffusion: Auto-Regressive Diffusion Model for Text GenerationCode1
Boosting Theory-of-Mind Performance in Large Language Models via PromptingCode1
Guiding Pretraining in Reinforcement Learning with Large Language ModelsCode1
Exploring the Benefits of Training Expert Language Models over Instruction TuningCode1
Large Language Models are Better Reasoners with Self-VerificationCode1
Layout-aware Dreamer for Embodied Referring Expression GroundingCode1
Behavior Cloned Transformers are Neurosymbolic ReasonersCode1
Task Compass: Scaling Multi-task Pre-training with Task PrefixCode1
Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersCode1
Large Language Models are Pretty Good Zero-Shot Video Game Bug DetectorsCode1
Leveraging Large (Visual) Language Models for Robot 3D Scene UnderstandingCode1
TextWorldExpress: Simulating Text Games at One Million Steps Per SecondCode1
Rethinking Alignment in Video Super-Resolution TransformersCode1
Multi-label Classification with High-rank and High-order Label CorrelationsCode1
Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and ReasoningCode1
UL2: Unifying Language Learning ParadigmsCode1
Learning to Detect Mobile Objects from LiDAR Scans Without LabelsCode1
AbductionRules: Training Transformers to Explain Unexpected InputsCode1
PACS: A Dataset for Physical Audiovisual CommonSense ReasoningCode1
SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware NormalizationCode1
Resolving label uncertainty with implicit posterior modelsCode1
A Dataset for Interactive Vision-Language Navigation with Unknown Command FeasibilityCode1
Comprehensive Visual Question Answering on Point Clouds through Compositional Scene ManipulationCode1
Reflash Dropout in Image Super-ResolutionCode1
The Web Is Your Oyster -- Knowledge-Intensive NLP against a Very Large Web CorpusCode1
Human Parity on CommonsenseQA: Augmenting Self-Attention with External AttentionCode1
RuleBert: Teaching Soft Rules to Pre-trained Language ModelsCode1
KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational GraphsCode1
HeadlineCause: A Dataset of News Headlines for Detecting CausalitiesCode1
Mention Flags (MF): Constraining Transformer-based Text GeneratorsCode1
MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem SolvingCode1
Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense ReasoningCode1
DialogSum: A Real-Life Scenario Dialogue Summarization DatasetCode1
Playing Codenames with Language Graphs and Word EmbeddingsCode1
Why AI is Harder Than We ThinkCode1
Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual EnvironmentsCode1
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question AnsweringCode1
Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World KnowledgeCode1
Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model AlignmentsCode1
UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask BenchmarkCode1
EventPlus: A Temporal Event Understanding PipelineCode1
Grounding Consistency: Distilling Spatial Common Sense for Precise Visual Relationship DetectionCode1
Fusing Context Into Knowledge Graph for Commonsense Question AnsweringCode1
How Can We Know When Language Models Know? On the Calibration of Language Models for Question AnsweringCode1
ConceptBert: Concept-Aware Representation for Visual Question AnsweringCode1
Show:102550
← PrevPage 3 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