https://github.com/lezhang7/rearank
공식 코드REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
A methodology that involves selecting relevant data or examples from a large dataset to support tasks like prediction, learning, or inference. It enhances models by providing context or additional information, often used in systems like retrieval-augmented generation or in-context learning.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
Exploring the Best Practices of Query Expansion with Large Language Models
BERT Has Uncommon Sense: Similarity Ranking for Word Sense BERTology
FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation
COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval
Socializing the Semantic Gap: A Comparative Survey on Image Tag Assignment, Refinement and Retrieval
SEA: Sentence Encoder Assembly for Video Retrieval by Textual Queries
URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression
The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation
Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval
ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generation
Listwise Generative Retrieval Models via a Sequential Learning Process
THUIR@COLIEE 2023: More Parameters and Legal Knowledge for Legal Case Entailment
Summarization-Based Document IDs for Generative Retrieval with Language Models
Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval
Challenges in Generalization in Open Domain Question Answering
T2VIndexer: A Generative Video Indexer for Efficient Text-Video Retrieval
CLIP-Event: Connecting Text and Images with Event Structures
Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person Retrieval
Retrieval augmentation of large language models for lay language generation
MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction
HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training
Enhancing Historical Image Retrieval with Compositional Cues
Retrieval Augmented Visual Question Answering with Outside Knowledge
Generative Recommendation: Towards Next-generation Recommender Paradigm
SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval
Revisiting the Role of Language Priors in Vision-Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.