Pith. sign in

REVIEW 5 cited by

Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2009.12756 v2 pith:WYIMZ3IT submitted 2020-09-27 cs.CL

Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

Wenhan Xiong , Xiang Lorraine Li , Srini Iyer , Jingfei Du , Patrick Lewis , William Yang Wang , Yashar Mehdad , Wen-tau Yih
show 3 more authors
Sebastian Riedel Douwe Kiela Barlas O\u{g}uz
This is my paper
classification cs.CL
keywords multi-hopansweringcomplexdensehotpotqaopen-domainquestionsretrieval
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose a simple and efficient multi-hop dense retrieval approach for answering complex open-domain questions, which achieves state-of-the-art performance on two multi-hop datasets, HotpotQA and multi-evidence FEVER. Contrary to previous work, our method does not require access to any corpus-specific information, such as inter-document hyperlinks or human-annotated entity markers, and can be applied to any unstructured text corpus. Our system also yields a much better efficiency-accuracy trade-off, matching the best published accuracy on HotpotQA while being 10 times faster at inference time.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation

    cs.IR 2026-02 unverdicted novelty 7.0

    AtomicRAG replaces chunk-based and triple-based GraphRAG with atom-entity graphs that store facts as atomic units and use personalized PageRank plus relevance filtering to achieve higher retrieval accuracy and reasoni...

  2. Retrieving a Set, Not Independent Passages: Set-Level Compatibility Learning for Efficient Set Exploration

    cs.IR 2026-07 conditional novelty 6.5

    Set-level margin training that ranks complete gold-compatible passage sets above incomplete or noisy ones, implemented with ParaSet exploration and SetCE reranking, improves multi-hop retrieval and QA and complements ...

  3. EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval

    cs.AI 2026-04 unverdicted novelty 6.0

    EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming ...

  4. HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering

    cs.AI 2026-06 reject novelty 5.0

    Organizing retrieved evidence into confidence-scored hypergraph chains is reported to lift multi-hop QA accuracy, context relevance, and faithfulness by 11–30 points over vector and graph RAG baselines on five benchmarks.

  5. DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent

    cs.AI 2026-03 conditional novelty 5.0

    A synthetic benchmark of 9,000 multi-hop web-research questions with difficulty tiers and teacher-generated search trajectories, plus an open-source RL training framework that reportedly lets 3B-parameter agents beat ...