# Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs

arXiv: https://arxiv.org/abs/1908.00469 · HTML: https://mlsanity.com/paper/1908.00469/

## Key facts

- Cited by 21 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 1 Aug 2019.

## Built on by (most cited first, 21 of 21)

- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [Complex Temporal Question Answering on Knowledge Graphs](https://mlsanity.com/paper/2109.08935/) (2021)
- [Complex Knowledge Base Question Answering: A Survey](https://mlsanity.com/paper/2108.06688/) (2021)
- [Conversational Question Answering: A Survey](https://mlsanity.com/paper/2106.00874/) (2021)
- [Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation](https://mlsanity.com/paper/2212.08632/) (2022)
- [Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering](https://mlsanity.com/paper/2109.07009/) (2021)
- [Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2105.04850/) (2021)
- [UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text](https://mlsanity.com/paper/2108.08614/) (2021)
- [Complex Factoid Question Answering with a Free-Text Knowledge Graph](https://mlsanity.com/paper/2103.12876/) (2021)
- [Beyond NED: Fast and Effective Search Space Reduction for Complex Question Answering over Knowledge Bases](https://mlsanity.com/paper/2108.08597/) (2021)
- [HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations](https://mlsanity.com/paper/2108.05774/) (2021)
- [A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering](https://mlsanity.com/paper/2104.08443/) (2021)
- [GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluation](https://mlsanity.com/paper/2508.16994/) (2025)
- [When to Use What: An In-Depth Comparative Empirical Analysis of OpenIE Systems for Downstream Applications](https://mlsanity.com/paper/2211.08228/) (2022)
- [Untargeted Adversarial Attack on Knowledge Graph Embeddings](https://mlsanity.com/paper/2405.10970/) (2024)
- [An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms](https://mlsanity.com/paper/2410.17694/) (2024)
- [MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation](https://mlsanity.com/paper/2504.08756/) (2025)
- [Recent Advances in Automated Question Answering In Biomedical Domain](https://mlsanity.com/paper/2111.05937/) (2021)
- [BigText-QA: Question Answering over a Large-Scale Hybrid Knowledge Graph](https://mlsanity.com/paper/2212.05798/) (2022)
- [textitBenchIEFL : A Manually Re-Annotated Fact-Based Open Information Extraction Benchmark](https://mlsanity.com/paper/2407.16860/) (2024)
- [LiCQA : A Lightweight Complex Question Answering System](https://mlsanity.com/paper/2602.22182/) (2026)

## Abstract (arXiv)

Direct answering of questions that involve multiple entities and relations is a challenge for text-based QA. This problem is most pronounced when answers can be found only by joining evidence from multiple documents. Curated knowledge graphs (KGs) may yield good answers, but are limited by their inherent incompleteness and potential staleness. This paper presents QUEST, a method that can answer complex questions directly from textual sources on-the-fly, by computing similarity joins over partial results from different documents. Our method is completely unsupervised, avoiding training-data bottlenecks and being able to cope with rapidly evolving ad hoc topics and formulation style in user questions. QUEST builds a noisy quasi KG with node and edge weights, consisting of dynamically retrieved entity names and relational phrases. It augments this graph with types and semantic alignments, and computes the best answers by an algorithm for Group Steiner Trees. We evaluate QUEST on benchmarks of complex questions, and show that it substantially outperforms state-of-the-art baselines.