Knowledge Graphs
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 4
- 보존된 평가 기록
- 19
A knowledge graph is a structured representation of information that organizes data into nodes (entities) and edges (relationships) to show how different pieces of knowledge are interconnected. It enables enhanced data integration, search, and inference by modeling the relationships between concepts and entities in a graph format.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/kxinwang2023/enco
공식 코드Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning
https://github.com/kyle8581/Web-Shepherd
공식 코드https://github.com/kylrth/procedure-generation
공식 코드Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&A
https://github.com/kynewang/prolink
공식 코드LLM as Prompter: Low-resource Inductive Reasoning on Arbitrary Knowledge Graphs
https://github.com/kyutai-labs/moshi
공식 코드Moshi: a speech-text foundation model for real-time dialogue
https://github.com/l8cv/busterx
공식 코드BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation
https://github.com/lab-v2/chatgpt_mwp_eval
공식 코드An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)
https://github.com/lab-v2/diversity_measures
공식 코드Diversity Measures: Domain-Independent Proxies for Failure in Language Model Queries
https://github.com/lab-v2/pyreason
공식 코드https://github.com/laihaoran/carzero
공식 코드CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification
https://github.com/laiyuzhi/nvp-hri
공식 코드NVP-HRI: Zero Shot Natural Voice and Posture-based Human-Robot Interaction via Large Language Model
https://github.com/lakeraai/dsec-gandalf
공식 코드https://github.com/lamda-rl/imaginebench
공식 코드ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts
https://github.com/lamm-mit/PRefLexOR
공식 코드In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR
https://github.com/lamm-mit/SciAgentsDiscovery
공식 코드SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning
https://github.com/lamm-mit/graphreasoning
공식 코드https://github.com/lamm-mit/lifegpt
공식 코드LifeGPT: Topology-Agnostic Generative Pretrained Transformer Model for Cellular Automata
https://github.com/lamm-mit/mechagents
공식 코드https://github.com/lamm-mit/peptideminer
공식 코드Learning the rules of peptide self-assembly through data mining with large language models
https://github.com/lamm-mit/protagents
공식 코드https://github.com/lamp-benchmark/lamp
공식 코드https://github.com/lanjiuqing64/kgdata
공식 코드ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs
https://github.com/lanl/t-elf
공식 코드HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation Learning
https://github.com/lanyu0303/afl
공식 코드Agentic Feedback Loop Modeling Improves Recommendation and User Simulation
https://github.com/lanzer-tree/ras-eval
공식 코드https://github.com/lanzhang128/retrieval_augmented_autoformalization
공식 코드Consistent Autoformalization for Constructing Mathematical Libraries
https://github.com/laowangzi/cikgrec
공식 코드Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models
https://github.com/laquabe/OneNet
공식 코드OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting
https://github.com/laquabe/know3rag
공식 코드Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering
https://github.com/lars-research/adaprop
공식 코드AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning
https://github.com/lars-research/knowddi
공식 코드Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning
https://github.com/lautaroest/sucpa-convergence
공식 코드https://github.com/lautel/meg
공식 코드MEG: Medical Knowledge-Augmented Large Language Models for Question Answering
https://github.com/lava-lab/cool-mc
공식 코드https://github.com/lavieenrose365/rella
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.