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 801–850 of 939 papers

TitleStatusHype
KnowZRel: Common Sense Knowledge-based Zero-Shot Relationship Retrieval for Generalised Scene Graph GenerationCode0
Towards One-Shot Learning for Text Classification using Inductive Logic ProgrammingCode0
Knowledge-Driven Robot Program Synthesis from Human VR DemonstrationsCode0
Retrieval Augmented Generation using Engineering Design KnowledgeCode0
KC-ISA: An Implicit Sentiment Analysis Model Combining Knowledge Enhancement and Context FeaturesCode0
COPA-SSE: Semi-structured Explanations for Commonsense ReasoningCode0
Extracting Commonsense Properties from Embeddings with Limited Human GuidanceCode0
COPAL-ID: Indonesian Language Reasoning with Local Culture and NuancesCode0
Large Language Models Need Consultants for Reasoning: Becoming an Expert in a Complex Human System Through Behavior SimulationCode0
Exploring Large Language Models as a Source of Common-Sense Knowledge for RobotsCode0
Exploiting Sentiment and Common Sense for Zero-shot Stance DetectionCode0
“It doesn’t look good for a date”: Transforming Critiques into Preferences for Conversational Recommendation SystemsCode0
Contextualized Scene Imagination for Generative Commonsense ReasoningCode0
Learn How to Cook a New Recipe in a New House: Using Map Familiarization, Curriculum Learning, and Bandit Feedback to Learn Families of Text-Based Adventure GamesCode0
Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference ResolutionCode0
VASR: Visual Analogies of Situation RecognitionCode0
Towards Symbolic Reinforcement Learning with Common SenseCode0
Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label DistributionsCode0
The Sensitivity of Language Models and Humans to Winograd Schema PerturbationsCode0
Explain Yourself! Leveraging Language Models for Commonsense ReasoningCode0
"It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation SystemsCode0
Learning Low-Level Causal Relations using a Simulated Robotic ArmCode0
Explainable Inference on Sequential Data via Memory-TrackingCode0
Asking the Right Question: Inferring Advice-Seeking Intentions from Personal NarrativesCode0
Every Answer Matters: Evaluating Commonsense with Probabilistic MeasuresCode0
Empirical Analysis of Foundational Distinctions in Linked Open DataCode0
Symbolic image detection using scene and knowledge graphsCode0
Robustness to Spurious Correlations via Human AnnotationsCode0
A Simple Method for Commonsense ReasoningCode0
Learning structure-aware semantic segmentation with image-level supervisionCode0
ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common SenseCode0
Is "My Favorite New Movie" My Favorite Movie? Probing the Understanding of Recursive Noun PhrasesCode0
Embodied Image Quality Assessment for Robotic IntelligenceCode0
Compositional Language Understanding with Text-based Relational ReasoningCode0
What the HellaSwag? On the Validity of Common-Sense Reasoning BenchmarksCode0
Embarrassingly Simple Performance Prediction for Abductive Natural Language InferenceCode0
Common Sense Bias in Semantic Role LabelingCode0
iREL at SemEval-2024 Task 9: Improving Conventional Prompting Methods for Brain TeasersCode0
A little less conversation, a little more action, please: Investigating the physical common-sense of LLMs in a 3D embodied environmentCode0
Tackling Domain-Specific Winograd Schemas with Knowledge-Based Reasoning and Machine LearningCode0
CommonGen: A Constrained Text Generation Challenge for Generative Commonsense ReasoningCode0
Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded ConversationCode0
Leveraging QA Datasets to Improve Generative Data AugmentationCode0
Elaboration-Generating Commonsense Question Answering at ScaleCode0
An Analysis of Dataset Overlap on Winograd-Style TasksCode0
Collaborative Synthesis of Patient Records through Multi-Visit Health State InferenceCode0
CODAH: An Adversarially Authored Question-Answer Dataset for Common SenseCode0
Information Gain Is Not All You NeedCode0
Inferring spatial relations from textual descriptions of imagesCode0
A Language Agent for Autonomous DrivingCode0
Show:102550
← PrevPage 17 of 19Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ST-MoE-32B 269B (fine-tuned)Accuracy96.1—Unverified
2Unicorn 11B (fine-tuned)Accuracy91.3—Unverified
3CompassMTL 567M with TailorAccuracy90.5—Unverified
4CompassMTL 567MAccuracy89.6—Unverified
5UnifiedQA 11B (fine-tuned)Accuracy89.4—Unverified
6Claude 3 Opus (5-shot)Accuracy88.5—Unverified
7GPT-4 (5-shot)Accuracy87.5—Unverified
8ExDeBERTa 567MAccuracy87—Unverified
9LLaMA-2 13B + MixLoRAAccuracy86.3—Unverified
10LLaMA3 8B+MoSLoRAAccuracy85.8—Unverified
#ModelMetricClaimedVerifiedStatus
1GPT-4 (few-shot, k=25)Accuracy96.4—Unverified
2PaLM 2 (few-shot, CoT, SC)Accuracy95.1—Unverified
3Shivaay (4B, few-shot, k=8)Accuracy91.04—Unverified
4StupidLLMAccuracy91.03—Unverified
5Claude 2 (few-shot, k=5)Accuracy91—Unverified
6Claude 1.3 (few-shot, k=5)Accuracy90—Unverified
7PaLM 540B (Self Improvement, Self Consistency)Accuracy89.8—Unverified
8PaLM 540B (Self Consistency)Accuracy88.7—Unverified
9PaLM 540B (Self Improvement, CoT Prompting)Accuracy88.3—Unverified
10PaLM 540B (Self Improvement, Standard-Prompting)Accuracy87.2—Unverified
#ModelMetricClaimedVerifiedStatus
1ST-MoE-32B 269B (fine-tuned)Accuracy95.2—Unverified
2LLaMA 3 8B+MoSLoRA (fine-tuned)Accuracy90.5—Unverified
3PaLM 2-L (1-shot)Accuracy89.7—Unverified
4PaLM 2-M (1-shot)Accuracy88—Unverified
5LLaMA-3 8B + MixLoRAAccuracy86.5—Unverified
6Camelidae-8×34BAccuracy86.2—Unverified
7PaLM 2-S (1-shot)Accuracy85.6—Unverified
8LLaMA 65B + CFG (0-shot)Accuracy84.2—Unverified
9GAL 120B (0-shot)Accuracy83.8—Unverified
10LLaMA-2 13B + MixLoRAAccuracy83.5—Unverified
#ModelMetricClaimedVerifiedStatus
1Turing NLR v5 XXL 5.4B (fine-tuned)EM95.9—Unverified
2ST-MoE-32B 269B (fine-tuned)EM95.1—Unverified
3T5-11BF194.1—Unverified
4DeBERTa-1.5BEM94.1—Unverified
5PaLM 540B (finetuned)EM94—Unverified
6Vega v2 6B (fine-tuned)EM93.9—Unverified
7PaLM 2-L (one-shot)F193.8—Unverified
8T5-XXL 11B (fine-tuned)EM93.4—Unverified
9PaLM 2-M (one-shot)F192.4—Unverified
10PaLM 2-S (one-shot)F192.1—Unverified