https://github.com/dthulke/dstc9-track1
공식 코드Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog
Papers with Code 아카이브
Retrieval-augmented Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/dwlmt/story-fragments
공식 코드Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories
https://github.com/edisonni-hku/diras
공식 코드DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation
https://github.com/ejaasaari/lorann
공식 코드LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
https://github.com/ejaasaari/lorann-experiments
공식 코드LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
https://github.com/elakhatibi/cdf-rag
공식 코드CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation
https://github.com/eliaslumer/graph-rag-tool-fusion-toollinkos
공식 코드https://github.com/elviswxy/rag_fairness
공식 코드Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems
https://github.com/emory-irlab/conqret-rag
공식 코드ConQRet: Benchmarking Fine-Grained Evaluation of Retrieval Augmented Argumentation with LLM Judges
https://github.com/epfl-dlab/llm-grounding-analysis
공식 코드A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
https://github.com/ericlee878/ScienceDeJargonizer
공식 코드De-jargonizing Science for Journalists with GPT-4: A Pilot Study
https://github.com/eustema-s-p-a/scarf
공식 코드https://github.com/everm0re/erarag-official
공식 코드EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora
https://github.com/evolvinglmms-lab/multimodal-search-r1
공식 코드https://github.com/exploration-lab/iitk-semeval-2024-task-2-clinical-nli
공식 코드https://github.com/facebookresearch/crag
공식 코드https://github.com/facebookresearch/dp_rdm
공식 코드DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
https://github.com/fangshiyuu/codrivingllm
공식 코드https://github.com/fate-ubw/raglab
공식 코드RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
https://github.com/fede-stack/adaptive-rag-for-psychological-assessment
공식 코드https://github.com/flagopen/flagembedding
공식 코드Flexibly Scaling Large Language Models Contexts Through Extensible Tokenization
https://github.com/florin-git/Base-vs-Instruct-LLMs-in-RAG-Systems
공식 코드A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems
https://github.com/florin-git/The-Power-of-Noise
공식 코드https://github.com/flyfree5/lahore
공식 코드Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval
https://github.com/franciszchen/surgbox
공식 코드SurgBox: Agent-Driven Operating Room Sandbox with Surgery Copilot
https://github.com/franco-galante/rgb-model
공식 코드Information Retrieval in the Age of Generative AI: The RGB Model
https://github.com/fraunhofer-iais/chunking-strategies
공식 코드Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis
https://github.com/freedomintelligence/huatuo-26m
공식 코드https://github.com/freedomintelligence/rag-instruct
공식 코드RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions
https://github.com/frontierlabs/mapdia
공식 코드Interpersonal Memory Matters: A New Task for Proactive Dialogue Utilizing Conversational History
https://github.com/fudandisc/disc-finllm
공식 코드DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning
https://github.com/fusion-jena/automatic-kg-creation-with-llm
공식 코드https://github.com/fusion-jena/information-retrieval-using-multiple-llm-and-rag
공식 코드https://github.com/futuredialchallenge/2024-rag
공식 코드The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG)
https://github.com/futureeeeee/dynamic-rag
공식 코드https://github.com/futureeeeee/mba
공식 코드MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.