Semantic Sentence Composition Reasoning for Multi-Hop Question Answering
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
Abstract (arXiv)
Due to the lack of insufficient data, existing multi-hop open domain question answering systems require to effectively find out relevant supporting facts according to each question. To alleviate the challenges of semantic factual sentences retrieval and multi-hop context expansion, we present a semantic sentence composition reasoning approach for a multi-hop question answering task, which consists of two key modules: a multi-stage semantic matching module (MSSM) and a factual sentence composition module (FSC). With the combination of factual sentences and multi-stage semantic retrieval, our approach can provide more comprehensive contextual information for model training and reasoning. Experimental results demonstrate our model is able to incorporate existing pre-trained language models and outperform the existing SOTA method on the QASC task with an improvement of about 9%.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 32 references that are in the map. First posted on arXiv 1 Mar 2022.
Builds on
21 of 32 references.
References · 21
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
- 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
- 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
- 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
- 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 851
- 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
- 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
- 2019QASC: A Dataset for Question Answering via Sentence Compositioncited by 248
- 2019Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documentscited by 57
9 more
- 2019Careful Selection of Knowledge to solve Open Book Question Answeringcited by 35
- 2019Multi-Hop Paragraph Retrieval for Open-Domain Question Answeringcited by 34
- 2015A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representationscited by 32
- 2019MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehensioncited by 20
- 2019Course Concept Expansion in MOOCs with External Knowledge and Interactive Gamecited by 14
- 2018A Deep Cascade Model for Multi-Document Reading Comprehensioncited by 11
- 2019Modeling Semantic Compositionality with Sememe Knowledgecited by 8
- 2019What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answeringcited by 7
- 2018Training a Ranking Function for Open-Domain Question Answeringcited by 4
Built on by
Citing papers per year: 2022: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering
- 2026Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends
- 2023Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning
- 2022Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering
- 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge
- 2024Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
- 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph
- 2025Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysis