# Differentiable Open-Ended Commonsense Reasoning

arXiv: https://arxiv.org/abs/2010.14439 · HTML: https://mlsanity.com/paper/2010.14439/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2020.

## Built on by (most cited first, 29 of 29)

- [CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge](https://mlsanity.com/paper/2109.01653/) (2021)
- [Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge](https://mlsanity.com/paper/2102.03315/) (2021)
- [RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge](https://mlsanity.com/paper/2101.00376/) (2021)
- [Natural Language Reasoning, A Survey](https://mlsanity.com/paper/2303.14725/) (2023)
- [The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus](https://mlsanity.com/paper/2112.09924/) (2021)
- [A Systematic Investigation of Commonsense Knowledge in Large Language Models](https://mlsanity.com/paper/2111.00607/) (2021)
- [Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above](https://mlsanity.com/paper/2502.14127/) (2025)
- [Unsupervised Cross-Task Generalization via Retrieval Augmentation](https://mlsanity.com/paper/2204.07937/) (2022)
- [Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment](https://mlsanity.com/paper/2203.14987/) (2022)
- [Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration](https://mlsanity.com/paper/2107.11879/) (2021)
- [Retrieval Augmentation for Commonsense Reasoning: A Unified Approach](https://mlsanity.com/paper/2210.12887/) (2022)
- [Empowering Language Models with Knowledge Graph Reasoning for Question Answering](https://mlsanity.com/paper/2211.08380/) (2022)
- [Probing Commonsense Explanation in Dialogue Response Generation](https://mlsanity.com/paper/2104.09574/) (2021)
- [Understanding Finetuning for Factual Knowledge Extraction from Language Models](https://mlsanity.com/paper/2301.11293/) (2023)
- [Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems](https://mlsanity.com/paper/2203.10610/) (2022)
- [Inferring Implicit Relations in Complex Questions with Language Models](https://mlsanity.com/paper/2204.13778/) (2022)
- [RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees](https://mlsanity.com/paper/2210.17095/) (2022)
- [Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs](https://mlsanity.com/paper/2307.01933/) (2023)
- [Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder](https://mlsanity.com/paper/2210.06230/) (2022)
- [Decker: Double Check with Heterogeneous Knowledge for Commonsense Fact Verification](https://mlsanity.com/paper/2305.05921/) (2023)
- [ActionReasoningBench: Reasoning about Actions with and without Ramification Constraints](https://mlsanity.com/paper/2406.04046/) (2024)
- [CoSe-Co: Text Conditioned Generative CommonSense Contextualizer](https://mlsanity.com/paper/2206.05706/) (2022)
- [Detecting Euphemisms with Literal Descriptions and Visual Imagery](https://mlsanity.com/paper/2211.04576/) (2022)
- [A Graph-Guided Reasoning Approach for Open-ended Commonsense Question Answering](https://mlsanity.com/paper/2303.10395/) (2023)
- [CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models](https://mlsanity.com/paper/2307.12382/) (2023)
- [Template Filling for Controllable Commonsense Reasoning](https://mlsanity.com/paper/2111.00539/) (2021)
- [Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts](https://mlsanity.com/paper/2201.02740/) (2021)
- [Open-ended Commonsense Reasoning with Unrestricted Answer Scope](https://mlsanity.com/paper/2310.11672/) (2023)
- [Explanation Quality Assessment as Ranking with Listwise Rewards](https://mlsanity.com/paper/2604.24176/) (2026)

## Abstract (arXiv)

Current commonsense reasoning research focuses on developing models that use commonsense knowledge to answer multiple-choice questions. However, systems designed to answer multiple-choice questions may not be useful in applications that do not provide a small list of candidate answers to choose from. As a step towards making commonsense reasoning research more realistic, we propose to study open-ended commonsense reasoning (OpenCSR) -- the task of answering a commonsense question without any pre-defined choices -- using as a resource only a corpus of commonsense facts written in natural language. OpenCSR is challenging due to a large decision space, and because many questions require implicit multi-hop reasoning. As an approach to OpenCSR, we propose DrFact, an efficient Differentiable model for multi-hop Reasoning over knowledge Facts. To evaluate OpenCSR methods, we adapt several popular commonsense reasoning benchmarks, and collect multiple new answers for each test question via crowd-sourcing. Experiments show that DrFact outperforms strong baseline methods by a large margin.