Papers with Code 아카이브
Logical Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 22
- 평가표
- 10
- 보존된 평가 기록
- 65
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/hkust-knowcomp/abductivekgr
공식 코드Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation
https://github.com/hkust-knowcomp/awesome-llm-scientific-discovery
공식 코드From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
https://github.com/hkust-knowcomp/efok-cqa
공식 코드$\text{EFO}_{k}$-CQA: Towards Knowledge Graph Complex Query Answering beyond Set Operation
https://github.com/hkust-knowcomp/lmpnn
공식 코드Logical Message Passing Networks with One-hop Inference on Atomic Formulas
https://github.com/hkust-knowcomp/sessioncqa
공식 코드Understanding Inter-Session Intentions via Complex Logical Reasoning
https://github.com/hkust-knowcomp/wfre
공식 코드https://github.com/hlr/nesycoco
공식 코드NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization
https://github.com/hlr/probabilistic_logical_reasoning
공식 코드https://github.com/hltchkust/chatgpt-evaluation
공식 코드https://github.com/hoar012/abil-kdd-2025
공식 코드Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation
https://github.com/holarissun/prompt-oirl
공식 코드Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
https://github.com/honghd16/ObstructedVLN
공식 코드Navigating Beyond Instructions: Vision-and-Language Navigation in Obstructed Environments
https://github.com/honghd16/vln-mp
공식 코드Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts
https://github.com/hope-rita/eifbench
공식 코드EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models
https://github.com/hsd1503/HOLMES
공식 코드HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
https://github.com/huanhuaneryuan/sr-plr
공식 코드Sequential Recommendation with Probabilistic Logical Reasoning
https://github.com/hxyz-123/reasoningocr
공식 코드Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?
https://github.com/hypatiaalegra/logicgame-data
공식 코드LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models
https://github.com/hzc1208/ANN2SNN_SRP
공식 코드Reducing ANN-SNN Conversion Error through Residual Membrane Potential
https://github.com/hzzzzzhappy/mc4ad
공식 코드Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection
https://github.com/ibm/ai-descartes
공식 코드AI Descartes: Combining Data and Theory for Derivable Scientific Discovery
https://github.com/ibm/neuro-vector-symbolic-architectures
공식 코드A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices
https://github.com/icongroupcwc/demo.percom23
공식 코드Codesign of Edge Intelligence and Automated Guided Vehicle Control
https://github.com/ifujisawa/addition-experiment
공식 코드Logical Tasks for Measuring Extrapolation and Rule Comprehension
https://github.com/ignc-research/habitatdyn
공식 코드HabitatDyn Dataset: Dynamic Object Detection to Kinematics Estimation
https://github.com/ignc-research/navsafe-arena
공식 코드https://github.com/iiis-ai/cumulative-reasoning
공식 코드https://github.com/ika-rwth-aachen/occuq
공식 코드OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction
https://github.com/ikr3-lab/ReasoningLLMs
공식 코드Reasoning Capabilities and Invariability of Large Language Models
https://github.com/ink-usc/fairr
공식 코드FaiRR: Faithful and Robust Deductive Reasoning over Natural Language
https://github.com/ink-usc/lifelong-icl
공식 코드Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
https://github.com/ink-usc/rationalemultirewarddistillation
공식 코드https://github.com/ink-usc/robustlr
공식 코드RobustLR: Evaluating Robustness to Logical Perturbation in Deductive Reasoning
https://github.com/insightllm/rl-without-gt
공식 코드https://github.com/inspirai/wilderness-scavenger
공식 코드WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environments
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.