mlsanityData to 7 Oct 2026

Open-ended Commonsense Reasoning with Unrestricted Answer Scope

arXiv 2310.11672 ↗First posted 18 Oct 2023cs.CLcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Open-ended Commonsense Reasoning is defined as solving a commonsense question without providing 1) a short list of answer candidates and 2) a pre-defined answer scope. Conventional ways of formulating the commonsense question into a question-answering form or utilizing external knowledge to learn retrieval-based methods are less applicable in the open-ended setting due to an inherent challenge. Without pre-defining an answer scope or a few candidates, open-ended commonsense reasoning entails predicting answers by searching over an extremely large searching space. Moreover, most questions require implicit multi-hop reasoning, which presents even more challenges to our problem. In this work, we leverage pre-trained language models to iteratively retrieve reasoning paths on the external knowledge base, which does not require task-specific supervision. The reasoning paths can help to identify the most precise answer to the commonsense question. We conduct experiments on two commonsense benchmark datasets. Compared to other approaches, our proposed method achieves better performance both quantitatively and qualitatively.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 24 of its 34 references that are in the map. First posted on arXiv 18 Oct 2023.

Builds on

24 of 34 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022GreaseLM: Graph REASoning Enhanced Language Models for Question Answering21 Jan

Other references · 23

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  5. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  6. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 475
  7. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  8. 2019QASC: A Dataset for Question Answering via Sentence Compositioncited by 248
  9. 2019KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoningcited by 216
  10. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  11. 2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
  12. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 134
11 more
  1. 2020Text-to-Text Pre-Training for Data-to-Text Taskscited by 104
  2. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45
  3. 2020Differentiable Open-Ended Commonsense Reasoningcited by 29
  4. 2021Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Taskscited by 24
  5. 2021Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformationcited by 19
  6. 2023Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategycited by 18
  7. 2021Distilling Relation Embeddings from Pre-trained Language Modelscited by 15
  8. 2023HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Promptingcited by 11
  9. 2020Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Pathscited by 8
  10. 2022Deep Generation of Heterogeneous Networkscited by 5
  11. 2023Knowledge-enhanced Neural Machine Reasoning: A Reviewcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023A Graph-Guided Reasoning Approach for Open-ended Commonsense Question Answering
  2. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge
  3. 2022CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm
  4. 2024BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering
  5. 2024ZEBRA: Zero-Shot Example-Based Retrieval Augmentation for Commonsense Question Answering
  6. 2026Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
  7. 2022TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering
  8. 2025ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering