An Interdisciplinary Review of Commonsense Reasoning and Intent Detection

2025/06/16 by Nazmus Sakib, Sakib, Md Nazmus
Computer Science · #Computation and Language (cs.CL) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC)

paper · pdf · doi:10.48550/arxiv.2506.14040

openalex publication_date 2025/06/16 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28

Abstract

This review explores recent advances in commonsense reasoning and intent detection, two key challenges in natural language understanding. We analyze 28 papers from ACL, EMNLP, and CHI (2020-2025), organizing them by methodology and application. Commonsense reasoning is reviewed across zero-shot learning, cultural adaptation, structured evaluation, and interactive contexts. Intent detection is examined through open-set models, generative formulations, clustering, and human-centered systems. By bridging insights from NLP and HCI, we highlight emerging trends toward more adaptive, multilingual, and context-aware models, and identify key gaps in grounding, generalization, and benchmark design.

Citations

• Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
• mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans
• Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge
• New Intent Discovery with Pre-training and Contrastive Learning
• Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce
• CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues
• Generated Knowledge Prompting for Commonsense Reasoning
• Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning
• Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models
• Energy-based Unknown Intent Detection with Data Manipulation
• Common Sense Beyond English: Evaluating and Improving Multilingual Language Models for Commonsense Reasoning
• OutFlip: Generating Out-of-Domain Samples for Unknown Intent Detection with Natural Language Attack
• ExplaGraphs: An Explanation Graph Generation Task for Structured\n Commonsense Reasoning
• The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation
• Differentiable Open-Ended Commonsense Reasoning
• "I'd rather just go to bed": Understanding Indirect Answers
• Unsupervised Commonsense Question Answering with Self-Talk
• QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions
• KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
• COMET: Commonsense Transformers for Automatic Knowledge Graph\n Construction

Related

• Generalized Zero-shot Intent Detection via Commonsense Knowledge
• Natural Language Processing with Commonsense Knowledge: A Survey
• Do Fine-tuned Commonsense Language Models Really Generalize?
• A Simple Machine Learning Method for Commonsense Reasoning? A Short Commentary on Trinh & Le (2018)
• CS-NLP team at SemEval-2020 Task 4: Evaluation of State-of-the-art NLP Deep Learning Architectures on Commonsense Reasoning Task