# Commonsense for Generative Multi-Hop Question Answering Tasks

arXiv: https://arxiv.org/abs/1809.06309 · HTML: https://mlsanity.com/paper/1809.06309/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2018.

## Built on by (most cited first, 30 of 48)

- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [Cumulative Reasoning with Large Language Models](https://mlsanity.com/paper/2308.04371/) (2023)
- [MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation](https://mlsanity.com/paper/2203.13560/) (2022)
- [Knowledge Graphs: Opportunities and Challenges](https://mlsanity.com/paper/2303.13948/) (2023)
- [ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models](https://mlsanity.com/paper/2303.16421/) (2023)
- [Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization](https://mlsanity.com/paper/2110.10834/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Biomedical knowledge graph-optimized prompt generation for large language models](https://mlsanity.com/paper/2311.17330/) (2023)
- [Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations](https://mlsanity.com/paper/2106.13876/) (2021)
- [Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation](https://mlsanity.com/paper/2101.00760/) (2021)
- [Exploring and Benchmarking the Planning Capabilities of Large Language Models](https://mlsanity.com/paper/2406.13094/) (2024)
- [Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices](https://mlsanity.com/paper/2112.03572/) (2021)
- [Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling](https://mlsanity.com/paper/2112.13556/) (2021)
- [Meta Prompting for AI Systems](https://mlsanity.com/paper/2311.11482/) (2023)
- [Self-Contradictory Reasoning Evaluation and Detection](https://mlsanity.com/paper/2311.09603/) (2023)
- [Zero-shot Commonsense Question Answering with Cloze Translation and Consistency Optimization](https://mlsanity.com/paper/2201.00136/) (2022)
- [Prix-LM: Pretraining for Multilingual Knowledge Base Construction](https://mlsanity.com/paper/2110.08443/) (2021)
- [Parameter-Efficient Abstractive Question Answering over Tables or Text](https://mlsanity.com/paper/2204.03357/) (2022)
- [ComFact: A Benchmark for Linking Contextual Commonsense Knowledge](https://mlsanity.com/paper/2210.12678/) (2022)
- [Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks](https://mlsanity.com/paper/2104.10193/) (2021)
- [Empathetic Response Generation through Graph-based Multi-hop Reasoning on Emotional Causality](https://mlsanity.com/paper/2110.04614/) (2021)
- [C3KG: A Chinese Commonsense Conversation Knowledge Graph](https://mlsanity.com/paper/2204.02549/) (2022)
- [Language Model Augmented Relevance Score](https://mlsanity.com/paper/2108.08485/) (2021)
- [Neural Multimodal Topic Modeling: A Comprehensive Evaluation](https://mlsanity.com/paper/2403.17308/) (2024)
- [Natural Language Processing with Commonsense Knowledge: A Survey](https://mlsanity.com/paper/2108.04674/) (2021)
- [Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs](https://mlsanity.com/paper/2210.10144/) (2022)
- [Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge](https://mlsanity.com/paper/2110.09698/) (2021)
- [ArT: All-round Thinker for Unsupervised Commonsense Question-Answering](https://mlsanity.com/paper/2112.13428/) (2021)
- [Generalizable Neuro-symbolic Systems for Commonsense Question Answering](https://mlsanity.com/paper/2201.06230/) (2022)

## Abstract (arXiv)

Reading comprehension QA tasks have seen a recent surge in popularity, yet most works have focused on fact-finding extractive QA. We instead focus on a more challenging multi-hop generative task (NarrativeQA), which requires the model to reason, gather, and synthesize disjoint pieces of information within the context to generate an answer. This type of multi-step reasoning also often requires understanding implicit relations, which humans resolve via external, background commonsense knowledge. We first present a strong generative baseline that uses a multi-attention mechanism to perform multiple hops of reasoning and a pointer-generator decoder to synthesize the answer. This model performs substantially better than previous generative models, and is competitive with current state-of-the-art span prediction models. We next introduce a novel system for selecting grounded multi-hop relational commonsense information from ConceptNet via a pointwise mutual information and term-frequency based scoring function. Finally, we effectively use this extracted commonsense information to fill in gaps of reasoning between context hops, using a selectively-gated attention mechanism. This boosts the model's performance significantly (also verified via human evaluation), establishing a new state-of-the-art for the task. We also show promising initial results of the generalizability of our background knowledge enhancements by demonstrating some improvement on QAngaroo-WikiHop, another multi-hop reasoning dataset.