Deterministic agentic-style multi-hop RAG at research-SOTA parity on commodity LLM APIs — no GPU, proof tree per answer.
-
Updated
Jun 23, 2026 - Python
#
multi-hop-qa
Here are 8 public repositories matching this topic...
7-layer RAG framework that eliminates semantic drift + context poisoning. Faithfulness 0.94 vs 0.71 Naive RAG. +13.6 EM on multi-hop QA.
python nlp machine-learning information-retrieval research ai deep-learning benchmarks question-answering semantic-search hallucination rag causal-reasoning llm langchain faithfulness retrieval-augmented-generation semantic-drift context-poisoning multi-hop-qa
-
Updated
Jun 24, 2026 - Python
Binary evidence-sufficiency dissociation in reasoning-model hidden states for fixed-question, changed-context multi-hop QA.
interpretability llm reasoning-models hidden-state-probing multi-hop-qa evidence-sufficiency mechanistic-dissociation
-
Updated
Apr 18, 2026 - Python
Knowledge-graph RAG for multi-hop QA: a controlled study that overturned its own +8.8 win under realistic evaluation.
-
Updated
Jun 20, 2026 - Python
A fine-tuned Qwen2.5-1.5B model that breaks complex multi-hop questions into atomic sub-queries with dependency graphs, doubling RAG retrieval accuracy in ~50ms
nlp information-retrieval lora fine-tuning rag huggingface llm qlora retrieval-augmented-generation orpo qwen2-5 query-decomposition multi-hop-qa
-
Updated
Jun 16, 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
Knowledge-graph RAG library for multi-hop QA — iterative retrieve-and-reason (IRCoT), graph retrieval, and cross-document enrichment at ingest. Production retrieval pipeline in Python.
python nlp information-retrieval retrieval embeddings knowledge-graph question-answering semantic-search bm25 ai-agents reranking rag vector-search hybrid-search llm llm-tools retrieval-augmented-generation graph-rag multi-hop-qa ircot
-
Updated
Jun 10, 2026 - Python
Official implementation of CHARM: Cascading Hallucination Aware Resolution and Mitigation for multi-step agentic RAG pipelines.
ai-safety nli rag cascade-detection langchain hallucination-detection agentic-ai llm-reliability multi-hop-qa
-
Updated
May 21, 2026 - Python
Improve this page
Add a description, image, and links to the multi-hop-qa topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the multi-hop-qa topic, visit your repo's landing page and select "manage topics."