Data to 14 Oct 2026

Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering

arXiv 1911.07176 ↗First posted 17 Nov 2019cs.CLcited by 59

Not on the map. Why?

Abstract (arXiv)

We propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) that (a) maximizes the relevance of the selected sentences, (b) minimizes the overlap between the selected facts, and (c) maximizes the coverage of both question and answer. This unsupervised sentence selection method can be coupled with any supervised QA approach. We show that the sentences selected by our method improve the performance of a state-of-the-art supervised QA model on two multi-hop QA datasets: AI2's Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC). We obtain new state-of-the-art performance on both datasets among approaches that do not use external resources for training the QA system: 56.82% F1 on ARC (41.24% on Challenge and 64.49% on Easy) and 26.1% EM0 on MultiRC. Our justification sentences have higher quality than the justifications selected by a strong information retrieval baseline, e.g., by 5.4% F1 in MultiRC. We also show that our unsupervised selection of justification sentences is more stable across domains than a state-of-the-art supervised sentence selection method.

Key facts. Cited by 59 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 8; 2023: 3; 2024: 16; 2025: 19; 2026: 7.

59 papers.

Sort:

By area:

2024ORPO: Monolithic Preference Optimization without Reference Modelcited by 562
2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 526
2023Who's Harry Potter? Approximate Unlearning in LLMscited by 381
2024Better & Faster Large Language Models via Multi-token Predictioncited by 360
2024The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bitscited by 308
2024Guardrail Baselines for Unlearning in LLMscited by 96
2024MARS: Unleashing the Power of Variance Reduction for Training Large Modelscited by 64
2021Evidentiality-guided Generation for Knowledge-Intensive NLP Taskscited by 40
2025BitNet b1.58 2B4T Technical Reportcited by 38
2025Tensor Product Attention Is All You Needcited by 31
2024Scalable MatMul-free Language Modelingcited by 25
2024Q-Sparse: All Large Language Models can be Fully Sparsely-Activatedcited by 25

38 more

2025JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Modelscited by 22
2024RECOST: External Knowledge Guided Data-efficient Instruction Tuningcited by 18
2025BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMscited by 18
2021Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answeringcited by 17
2022METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanationcited by 17
2022NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoningcited by 16
2021Exploiting Reasoning Chains for Multi-hop Science Question Answeringcited by 15
2024Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptationcited by 15
2022DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routingcited by 13
2025InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusioncited by 12
2022Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformerscited by 11
2024Exploring Quantization for Efficient Pre-Training of Transformer Language Modelscited by 10
2025Single-pass Detection of Jailbreaking Input in Large Language Modelscited by 10
2025Hardware-Efficient Attention for Fast Decodingcited by 10
2025MARS-M: When Variance Reduction Meets Matricescited by 10
2026Deep Delta Learningcited by 9
2025InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Modelscited by 8
2025GradPower: Powering Gradients for Faster Language Model Pre-Trainingcited by 8
2021Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inferencecited by 7
2024AI Benchmarks and Datasets for LLM Evaluationcited by 7
2025AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clippingcited by 6
2025TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edgecited by 6
2023HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervisioncited by 5
2025InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusioncited by 5
2025iFairy: the First 2-bit Complex LLM with All Parameters in ±1, ± icited by 5
2025Benchmarking and Improving LLM Robustness for Personalized Generationcited by 4
2021Encoding Explanatory Knowledge for Zero-shot Science Question Answeringcited by 3
2022Towards Better Few-Shot and Finetuning Performance with Forgetful Causal Language Modelscited by 3
2022Analyzing Multi-Task Learning for Abstractive Text Summarizationcited by 3
2024A Logical Pattern Memory Pre-trained Model for Entailment Tree Generationcited by 3
2024Cross-Architecture Transfer Learning for Linear-Cost Inference Transformerscited by 3
2026More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activationscited by 3
2023Mitigating Data Scarcity for Large Language Modelscited by 2
2024Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Modelscited by 2
2024TruncFormer: Private LLM Inference Using Only Truncationscited by 2
2025Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in ± 1, ± icited by 2
2026MI-PRUN: Optimize Large Language Model Pruning via Mutual Informationcited by 2
2026Multi-Head Low-Rank Attentioncited by 2

50 most cited of 59 All 59 (JSON)