The official implementation of ICLR 2020, "Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering".
-
Updated
Jul 25, 2024 - Python
#
hotpotqa
Here are 16 public repositories matching this topic...
Codes for NAACL 2021 Paper "Unsupervised Multi-hop Question Answering by Question Generation"
-
Updated
Nov 16, 2022 - Python
Implementation of Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation. Paper: https://arxiv.org/abs/2404.06809
-
Updated
Oct 22, 2024 - Python
Pytorch implementation of "A Simple Yet Strong Pipeline for HotpotQA" (Groeneveld, D., Khot, T., & Sabharwal, A.). Now developing!
-
Updated
Oct 7, 2020 - Python
Enhancing Retrieval-Augmented Generation with Document Link Structure for Multi-hop Web Question Answering
-
Updated
Apr 20, 2026 - Python
This codebase implements a Retrieval-Augmented Generation (RAG) chatbot using the Gemini API and DSPy framework, designed to answer questions based on the HotPotQA dataset. It includes components for loading data, generating responses, and evaluating model performance through various QA strategies, including basic QA and multi-hop retrieval.
-
Updated
Nov 3, 2024 - Python
Episodic Distillation for Verified RAG using Google Cloud + MongoDB Atlas
-
Updated
Jun 1, 2026 - JavaScript
Hallucination-resistant multi-hop QA using hybrid BM25+FAISS retrieval, cross-encoder reranking, citation selection, and NLI-based verification. Evaluated on HotpotQA (7,405 examples), zero-shot.
nlp question-answering bm25 zero-shot-learning reranking nli faiss rag multi-hop-reasoning hotpotqa cross-encoder llm bertscore ollama hallucination-detection gemma-4
-
Updated
May 26, 2026 - Python
Implementation of concepts of NLP
-
Updated
Feb 8, 2021 - Jupyter Notebook
LangGraph supervisor with parallel specialist agents. 1.99x speedup vs sequential multi-agent, reproducible in 6s with no API key. Planner, retrievers, analyzers, verifiers, synthesizer.
-
Updated
May 21, 2026 - Python
Agents Don't Always Do What They Think: Measuring Faithfulness in Multi-Step ReAct Agents
robustness perturbation-analysis hotpotqa chain-of-thought faithfulness llm-evaluation react-agent stanford-cs224n
-
Updated
Mar 16, 2026 - Python
Exploration of retrieval methods on the HotpotQA corpus, combining dense retrieval and feature-based reranking. Achieved a mean nDCG@10 of 0.9416 using LambdaRank with features such as cross-encoder score, LLM score, BM25 score, and token-based statistics—surpassing dense retriever + cross-encoder baselines.
retrieval retrieval-systems lambdarank hotpotqa cross-encoder dense-retrieval qa-reterival llm-ranking
-
Updated
Oct 31, 2025 - Python
RAG system with adaptive retrieval (Qdrant dense + sparse + RRF), cross-encoder re-ranking, and optional long-term memory (Mem0) — evaluated using HotpotQA EM/F1 on 5K questions. Dual-backend: runs locally via Ollama or via API. Dockerized.
python nlp docker evaluation reranking rag multi-hop-reasoning fastapi hotpotqa hybrid-search cross-encoder qdrant llm ollama langgraph ragas llm-as-judge agentic-rag mem0 deepeval
-
Updated
Apr 23, 2026 - Python
Local-only, graph-augmented, iteratively-reasoning, self-corrective RAG showcase on Apple Silicon — pushing toward published SOTA on multi-hop QA (MuSiQue, 2WikiMultiHopQA, HotpotQA) with HippoRAG 2 + Adaptive routing + Search-o1 iterative reasoning + CRAG-style gating + NLI faithfulness verification.
showcase mlx rag musique fastapi natural-questions streamlit hotpotqa colbert apple-silicon crag qdrant retrieval-augmented-generation graph-rag adaptive-rag hipporag qwen3 multi-hop-qa search-o1
-
Updated
May 30, 2026 - Python
Improve this page
Add a description, image, and links to the hotpotqa topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the hotpotqa topic, visit your repo's landing page and select "manage topics."