https://github.com/tangqiaoyu/selfretrieval
공식 코드Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Information retrieval is the task of ranking a list of documents or search results in response to a query
<span style="color:grey; opacity: 0.6">( Image credit: sudhanshumittal )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval
Declarative Experimentation in Information Retrieval using PyTerrier
Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval
Continual Learning of Long Topic Sequences in Neural Information Retrieval
SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval
Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System
VUS: Effective and Efficient Accuracy Measures for Time-Series Anomaly Detection
Optimizing Revenue while showing Relevant Assortments at Scale
Predicting Real-time Scientific Experiments Using Transformer models and Reinforcement Learning
Long-Range Transformer Architectures for Document Understanding
T2Ranking: A large-scale Chinese Benchmark for Passage Ranking
Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision
CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search
OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction
FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection
WebCPM: Interactive Web Search for Chinese Long-form Question Answering
Retrieval Augmented Generation based Large Language Models for Causality Mining
VDTuner: Automated Performance Tuning for Vector Data Management Systems
Teaching Smaller Language Models To Generalise To Unseen Compositional Questions
Goniometers are a Powerful Acoustic Feature for Music Information Retrieval Tasks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.