Query Expension for Better Query Embedding using LLMs
-
Updated
Feb 18, 2025 - Python
#
beir
Here are 25 public repositories matching this topic...
Code and models for the paper "Questions Are All You Need to Train a Dense Passage Retriever (TACL 2023)"
-
Updated
Dec 27, 2022 - Python
SPRINT Toolkit helps you evaluate diverse neural sparse models easily using a single click on any IR dataset.
-
Updated
Jul 25, 2023 - Python
Evaluation of BEIR Datasets using ColBERT retrieval model
-
Updated
Mar 4, 2022 - Python
A genral RAG Search chatbot, with SoTA RAG techniques such as HyDE, Hybrid retrieval with BM25 + RRF and Cross encoder reranking. Evaluated on the BEIR scifact dataset and compared all the different pipelines i tried along the way
-
Updated
Aug 23, 2025 - Python
Physics-Inspired Reranking via Token-Level Point Clouds & PDE Fusion | NFCorpus NDCG@10 = 0.3232 (+47.2%) | 26ms CPU | Zero training
-
Updated
Jun 3, 2026 - JavaScript
A decentralized cooperative memory & research layer for AI agents — collectively and cooperatively learning and advancing as a community.
ai memory mcp p2p knowledge-graph libp2p codex ai-agents rag vector-search local-first did-key beir llm federated-search sqlite-vec mcp-server agent-memory claude-code mem0-alternative
-
Updated
Jun 25, 2026 - TypeScript
GPU benchmark for RAG embedding compression and Faiss IVF-PQ ADC retrieval on FiQA / BEIR.
-
Updated
Jun 25, 2026 - Jupyter Notebook
SERA-VQ: Discrete codes for extreme embedding compression — outperforms PCA+int8 at low memory budgets on BEIR/SciFact
nlp machine-learning information-retrieval compression deep-learning retrieval embeddings nearest-neighbor-search pca quantization semantic-search similarity-search vector-quantization sentence-embeddings rag vector-search text-embeddings sentence-transformers beir residual-vector-quantization
-
Updated
May 2, 2026 - Python
RAG evaluation on BEIR SciFact: BM25, dense and hybrid retrieval with LLM answers.
-
Updated
Feb 1, 2026 - Jupyter Notebook
Research-grade hybrid retrieval API — BM25 + FAISS + CDF calibration + entropy-weighted fusion + cross-encoder reranking. Benchmarked on BEIR SciFact with bootstrap significance tests.
python nlp information-retrieval semantic-search bm25 faiss fastapi sentence-transformers hybrid-search beir
-
Updated
Jun 11, 2026 - Python
A RAG system that replaces standard BM25/FAISS retrieval with a fully learned neural retrieval stack - including a fine-tuned bi-encoder, a cross-encoder reranker, ColBERT-style late interaction scoring, and a locally hosted LLM generator. Built entirely with free and open-source tools.
nlp tensorflow pytorch machinelearning informationretrieval faiss semanticsearch rag mlops mlflow fastapi colbert crossencoder beir llm ollama llmengineering neuralretrieval
-
Updated
Apr 3, 2026 - Python
端到端 Hybrid RAG 系统 (BEIR/SciFact)：BM25 + Dense + Weighted Fusion + RAGAS 评估 + LLM-as-judge 稳定性研究
nlp information-retrieval bm25 faiss rag streamlit sentence-transformers hybrid-search dense-retrieval beir retrieval-augmented-generation llm-evaluation
-
Updated
Jun 1, 2026 - Python
Browser-side IR benchmark: BM25 vs Semantic vs Hybrid retrieval on SciFact (BEIR). Bauman MSTU NIR 2026.
react information-retrieval typescript webassembly semantic-search bm25 nir bauman beir transformers-js scifact
-
Updated
May 20, 2026 - TypeScript
Scripts to convert the LegalBench-RAG dataset into the standard IR format
-
Updated
May 31, 2025 - Python
BM25 & SBERT retrieval on the FiQA-2018 financial QA benchmark · Gradio demo
-
Updated
Apr 24, 2026 - Jupyter Notebook
Dense retrieval + cross-encoder reranking pipeline benchmarked on BEIR datasets (NDCG, Recall@K, MRR)
-
Updated
Apr 29, 2026 - Python
Cross-Family LLM-Judge Agreement for Institutional RAG: 5 families, 9 judges. Validated on TREC RAG 2024 (kappa=0.4941) + BEIR scifact.
information-retrieval cohens-kappa inter-rater-agreement beir retrieval-augmented-generation llm-as-judge meta-evaluation trec-rag institutional-search
-
Updated
May 17, 2026 - Python
Argument-Aware RAG with ensemble retrieval and stance-aware structured generation for explainable fact verification (BEIR-FEVER)
python nlp research transformers argumentation explainable-ai fact-verification beir retrieval-augmented-generation
-
Updated
Jun 24, 2026 - Jupyter Notebook
Controlled depth ablation of a BERT bi-encoder across training budgets and seeds on three BEIR tasks (nfcorpus, scifact, fiqa). L3–L12 is flat within seed noise at 20K steps; 80K training degrades every depth on zero-shot transfer (−45% NDCG@10 on fiqa for L12).
nlp information-retrieval pytorch embeddings reproducibility bert neural-ir ablation-studies sentence-transformers zero-shot-retrieval bi-encoder dense-retrieval beir ms-marco depth-ablation
-
Updated
Apr 24, 2026 - Python
Improve this page
Add a description, image, and links to the beir topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the beir topic, visit your repo's landing page and select "manage topics."