Papers with Code 아카이브
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/uva-dsa/dkec
공식 코드DKEC: Domain Knowledge Enhanced Multi-Label Classification for Diagnosis Prediction
https://github.com/vahe1994/spqr
공식 코드SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
https://github.com/vahidaz/llamarec-lkg-rag
공식 코드LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking
https://github.com/valence-labs/TxPert
공식 코드https://github.com/valentyn1boreiko/llm-threat-model
공식 코드A Realistic Threat Model for Large Language Model Jailbreaks
https://github.com/valuebyte-ai/awesome-llm-psychometrics
공식 코드Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement
https://github.com/vanderschaarlab/discopop
공식 코드Discovering Preference Optimization Algorithms with and for Large Language Models
https://github.com/vanderschaarlab/l2mac
공식 코드L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
https://github.com/vasilikikou/memegraphs
공식 코드https://github.com/vasiliskatr/faaf
공식 코드FaaF: Facts as a Function for the evaluation of generated text
https://github.com/vbdi/divprune
공식 코드DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models
https://github.com/vcahlik/reasoning-grounded-explanations
공식 코드Reasoning-Grounded Natural Language Explanations for Language Models
https://github.com/vcskaushik/LLMzip
공식 코드LLMZip: Lossless Text Compression using Large Language Models
https://github.com/vec-ai/wikihow-tiir
공식 코드https://github.com/vectara/FaithJudge
공식 코드Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
https://github.com/vectara/faithbench
공식 코드FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs
https://github.com/vectara/mirage-bench
공식 코드MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems
https://github.com/vectorinstitute/fed-rag
공식 코드FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems
https://github.com/vectozavr/llm-hessian
공식 코드Hessian of Perplexity for Large Language Models by PyTorch autograd (Open Source)
https://github.com/vectozavr/thanos
공식 코드Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression
https://github.com/vendi12/semantic_coherence
공식 코드https://github.com/verdurechen/sos-retrieval-loop
공식 코드https://github.com/veronicium/codebenchgen
공식 코드CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks
https://github.com/via-research/vtrain
공식 코드https://github.com/vicentvankor/sun-shine
공식 코드https://github.com/vicky-wil/monitor
공식 코드https://github.com/vid-koci/kbctransferlearning
공식 코드Pre-training and Diagnosing Knowledge Base Completion Models
https://github.com/vida-nyu/satori-assistance
공식 코드Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling
https://github.com/vijaydwivedi75/gnn-lspe
공식 코드Graph Neural Networks with Learnable Structural and Positional Representations
https://github.com/vinairesearch/recgpt
공식 코드RecGPT: Generative Pre-training for Text-based Recommendation
https://github.com/vinairesearch/whoqa
공식 코드Who's Who: Large Language Models Meet Knowledge Conflicts in Practice
https://github.com/vincentkoc/tiny_qa_benchmark_pp
공식 코드https://github.com/vinceouti/citynavagent
공식 코드https://github.com/vinhsuhi/wge
공식 코드Two-view Graph Neural Networks for Knowledge Graph Completion
https://github.com/vinsontang1/slidecoder
공식 코드SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.