Papers with Code 아카이브

Common Sense Reasoning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 17
평가표: 24
보존된 평가 기록: 397

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.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://bitbucket.org/luisespinosa/lr-nlp

공식 코드

The Interplay between Lexical Resources and Natural Language Processing

https://gitee.com/xiaoyibang/clipdrug

공식 코드

CLDR: Contrastive Learning Drug Response Models from Natural Language Supervision

https://github.com/1094701018/ketm

공식 코드

KETM:A Knowledge-Enhanced Text Matching method

https://github.com/18979705623/hspr

공식 코드

Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation

https://github.com/601175936/homi

공식 코드

Multi-label Classification with High-rank and High-order Label Correlations

https://github.com/Ayush8120/COAT

공식 코드

Physical Reasoning and Object Planning for Household Embodied Agents

https://github.com/CornellNLP/ASQ

공식 코드

Asking the Right Question: Inferring Advice-Seeking Intentions from Personal Narratives

https://github.com/DFKI-NLP/DISTRE

공식 코드

Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction

https://github.com/DebugML/sqrl

공식 코드

Do Machine Learning Models Learn Statistical Rules Inferred from Data?

https://github.com/DecstionBack/AAAI_2020_CommonsenseQA

공식 코드

Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering

https://github.com/HKUST-KnowComp/WinoWhy

공식 코드

WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge

https://github.com/HaozhiQi/RPIN

공식 코드

Learning Long-term Visual Dynamics with Region Proposal Interaction Networks

https://github.com/IBM/commonsense-rl

공식 코드

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines

https://github.com/INK-USC/CALM

공식 코드

Pre-training Text-to-Text Transformers for Concept-centric Common Sense

https://github.com/INK-USC/KagNet

공식 코드

KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning

https://github.com/INK-USC/XCSR

공식 코드

Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning

https://github.com/InstituteforDiseaseModeling/Bridging-the-Gap-Low-Resource-African-Languages

공식 코드

Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments

https://github.com/Ipazia-AI/latent-explorer

공식 코드

Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph

https://github.com/JetRunner/dogwhistle

공식 코드

Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge

https://github.com/Kinds-of-Intelligence-CFI/PredictaBoard

공식 코드

PredictaBoard: Benchmarking LLM Score Predictability

https://github.com/KlozeWang/LoSiA

공식 코드

LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization

https://github.com/LeapLabTHU/CheXWorld

공식 코드

CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning

https://github.com/Limmen/gym-idsgame

공식 코드

Finding Effective Security Strategies through Reinforcement Learning and Self-Play

https://github.com/LuanaBulla/Detection-of-Morality-in-Text

공식 코드

Do Language Models Understand Morality? Towards a Robust Detection of Moral Content

https://github.com/Mcibula/causal-learning-arm

공식 코드

Learning Low-Level Causal Relations using a Simulated Robotic Arm

https://github.com/Moradnejad/Predicting-Subjective-Features-on-QA-Websites

공식 코드

Predicting Subjective Features of Questions of QA Websites using BERT

https://github.com/NVlabs/GatedDeltaNet

공식 코드

Gated Delta Networks: Improving Mamba2 with Delta Rule

https://github.com/NickyFot/HitchhikersGuide

공식 코드

A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning

https://github.com/PJLab-ADG/DiLu

공식 코드

DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models

https://github.com/PJLab-ADG/driveLikeAHuman

공식 코드

Drive Like a Human: Rethinking Autonomous Driving with Large Language Models

https://github.com/PlusLabNLP/EventPlus

공식 코드

EventPlus: A Temporal Event Understanding Pipeline

https://github.com/QQBrowserVideoSearch/CBVS-UniCLIP

공식 코드

CBVS: A Large-Scale Chinese Image-Text Benchmark for Real-World Short Video Search Scenarios

https://github.com/RussianNLP/RussianSuperGLUE

공식 코드

RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark

https://github.com/ShootingWong/DomainRAG

공식 코드

DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation

https://github.com/SitLog/source_code

공식 코드

Deliberative and Conceptual Inference in Service Robots

https://github.com/TUDB-Labs/MixLoRA

공식 코드

MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.