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://github.com/malihealikhani/That_and_There

공식 코드

That and There: Judging the Intent of Pointing Actions with Robotic Arms

https://github.com/mandarjoshi90/pair2vec

공식 코드

pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference

https://github.com/mansicer/background-knowledge-rl

공식 코드

Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models

https://github.com/mbzuai-nlp/lamini-lm

공식 코드

LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions

https://github.com/mehdiazarafza/hybrid-reasoning

공식 코드

Hybrid Reasoning Based on Large Language Models for Autonomous Car Driving

https://github.com/mengyuanchen21/re-edl

공식 코드

Revisiting Essential and Nonessential Settings of Evidential Deep Learning

https://github.com/mhany90/enhanced_wsc

공식 코드

The Sensitivity of Language Models and Humans to Winograd Schema Perturbations

https://github.com/mhmdsaiid/rulebert

공식 코드

RuleBert: Teaching Soft Rules to Pre-trained Language Models

https://github.com/michelecafagna26/hl-dataset

공식 코드

HL Dataset: Visually-grounded Description of Scenes, Actions and Rationales

https://github.com/michiyasunaga/dragon

공식 코드

Deep Bidirectional Language-Knowledge Graph Pretraining

https://github.com/michiyasunaga/qagnn

공식 코드

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

https://github.com/microsoft/DEKCOR-CommonsenseQA

공식 코드

Fusing Context Into Knowledge Graph for Commonsense Question Answering

https://github.com/microsoft/DeBERTa

공식 코드

DeBERTa: Decoding-enhanced BERT with Disentangled Attention

https://github.com/microsoft/EA-VQ-VAE

공식 코드

Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder

https://github.com/microsoft/ProphetNet

공식 코드

AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation

https://github.com/microsoft/kear

공식 코드

Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention

https://github.com/midas-research/calling-out-bluff

공식 코드

Evaluation Toolkit For Robustness Testing Of Automatic Essay Scoring Systems

https://github.com/midas-research/interpreting-AES-Integrated-Gradients

공식 코드

My Teacher Thinks The World Is Flat! Interpreting Automatic Essay Scoring Mechanism

https://github.com/mikecovlee/DynMoLE

공식 코드

DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism

https://github.com/mikecovlee/mLoRA

공식 코드

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

https://github.com/mistralai/mistral-src

공식 코드

https://github.com/mit-han-lab/llm-awq

공식 코드

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

https://github.com/mit-spark/llm_scene_understanding

공식 코드

Leveraging Large (Visual) Language Models for Robot 3D Scene Understanding

https://github.com/morphology-probing/morph-call

공식 코드

Morph Call: Probing Morphosyntactic Content of Multilingual Transformers

https://github.com/mrwu-mac/R-Bench

공식 코드

Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models

https://github.com/nailashfrni/mcq-leakage-detection-code

공식 코드

Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation

https://github.com/namisan/mt-dnn

공식 코드

A Hybrid Neural Network Model for Commonsense Reasoning

https://github.com/nasrinkalanat/skg-sym

공식 코드

Symbolic image detection using scene and knowledge graphs

https://github.com/nbasyl/llm-fp4

공식 코드

LLM-FP4: 4-Bit Floating-Point Quantized Transformers

https://github.com/nickyfot/emocommonsense

공식 코드

VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning

https://github.com/nikozoe/human_ai_collectives

공식 코드

Human-AI collectives produce the most accurate differential diagnoses

https://github.com/nlp-anonymous-happy/anonymous-kg-guided-nlp

공식 코드

KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs

https://github.com/nogu-atsu/small-dataset-image-generation

공식 코드

Image Generation From Small Datasets via Batch Statistics Adaptation

https://github.com/normal-computing/extended-mind-transformers

공식 코드

Extended Mind Transformers

https://github.com/nvidia-cosmos/cosmos-reason1

공식 코드

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

https://github.com/nvidia/tensorrt-llm

공식 코드

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

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