Lune

EMNLP Findings2023

CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering

Weiqi Wang, Tianqing Fang, Wenxuan Ding, Baixuan Xu, Xin Liu, Yangqiu Song, Antoine Bosselut

Abstract

The task of zero-shot commonsense question answering evaluates models on their capacity to reason about general scenarios beyond those presented in specific datasets. Existing approaches for tackling this task leverage external knowledge from CommonSense Knowledge Bases (CSKBs) by pre-training the model on synthetic QA pairs constructed from CSKBs. In these approaches, negative examples (distractors) are formulated by randomly sampling from CSKBs using fairly primitive keyword constraints. However, two bottlenecks limit these approaches: the inherent incompleteness of CSKBs limits the semantic coverage of synthetic QA pairs, and the lack of human annotations makes the sampled negative examples potentially uninformative and contradictory.

To tackle these limitations above, we propose Conceptualization-Augmented Reasoner (CAR), a zero-shot commonsense questionanswering framework that fully leverages the power of conceptualization. Specifically, CAR abstracts a commonsense knowledge triple to many higher-level instances, which increases the coverage of the CSKB and expands the ground-truth answer space, reducing the likelihood of selecting false-negative distractors. Extensive experiments demonstrate that CAR more robustly generalizes to answering questions about zero-shot commonsense scenarios than existing methods, including large language models, such as GPT3.5 and Chat-GPT. Our code, data, and model checkpoints are available at https://github.com/HKUST- KnowComp/CAR.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

12 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora cites BERTScore: Evaluating Text Generation with BERT
  • Language Models are Few-Shot Learners cites WinoGrande: An Adversarial Winograd Schema Challenge at Scale
  • Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Training language models to follow instructions with human feedback
  • Training language models to follow instructions with human feedback cites Language Models are Few-Shot Learners
  • EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association cites Language Models are Few-Shot Learners
  • EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association cites Miko: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers12

  1. Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical ConstraintsJiaxin Bai, Xin Liu, Weiqi Wang, Chen Luo et al.NeurIPS 2023 · 46 citations
  2. AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale CorporaJiaxin Bai, Wei Fan, Qi Hu, Qing Zong et al.ACL 2026 · 27 citations
  3. Predicting Information Pathways Across Online CommunitiesYiqiao Jin, Yeon-Chang Lee, Kartik Sharma, Meng Ye et al.KDD 2023 · 18 citations
  4. EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product AssociationWeiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag et al.ACL 2025 · 15 citations
  5. Miko: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense DiscoveryFeihong Lu, Weiqi Wang, Yangyifei Luo, Ziqin Zhu et al.ACM MM 2024 · 11 citations

Builds on37

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
  3. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  4. BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
  5. WinoGrande: An Adversarial Winograd Schema Challenge at ScaleKeisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, Yejin ChoiAAAI 2020 · 3,037 citations

Related papers

  1. Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question AnsweringKaixin Ma, Filip Ilievski, Jonathan Francis, Yonatan Bisk et al.AAAI 2021 · 100 citations
  2. Zero-Shot Commonsense Question Answering with Cloze Translation and Consistency OptimizationZi-Yi Dou, Nanyun PengAAAI 2022 · 29 citations
  3. MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge RepresentationYing Su, Zihao Wang, Tianqing Fang, Hongming Zhang et al.EMNLP Findings 2022 · 13 citations
  4. ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense Question AnsweringFrancesco Molfese, Simone Conia, Riccardo Orlando, Roberto NavigliEMNLP 2024
  5. Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question AnsweringAntoine Bosselut, Ronan Le Bras, Yejin ChoiAAAI 2021 · 135 citations
Dusk over the sea between two cliffs drawn in fine vertical lines