DiscoSense: Commonsense Reasoning with Discourse Connectives
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
We present DiscoSense, a benchmark for commonsense reasoning via understanding a wide variety of discourse connectives. We generate compelling distractors in DiscoSense using Conditional Adversarial Filtering, an extension of Adversarial Filtering that employs conditional generation. We show that state-of-the-art pre-trained language models struggle to perform well on DiscoSense, which makes this dataset ideal for evaluating next-generation commonsense reasoning systems.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 29 of its 47 references that are in the map. First posted on arXiv 22 Oct 2022.
Builds on
29 of 47 references.
References · 29
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
- 2019The Curious Case of Neural Text Degenerationcited by 2,916
- 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
- 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
- 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
- 2015A large annotated corpus for learning natural language inferencecited by 1,847
- 2018Datasheets for Datasetscited by 1,386
- 2018Model Cards for Model Reportingcited by 1,080
- 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
17 more
- 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
- 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 556
- 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 378
- 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
- 2019Abductive Commonsense Reasoningcited by 301
- 2019Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoningcited by 285
- 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 255
- 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
- 2020Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processingcited by 162
- 2020Adversarial Filters of Dataset Biasescited by 160
- 2019"Going on a vacation" takes longer than "Going for a walk": A Study of Temporal Commonsense Understandingcited by 123
- 2021UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmarkcited by 98
- 2020Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoningcited by 65
- 2021TIMEDIAL: Temporal Commonsense Reasoning in Dialogcited by 55
- 2020ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoningcited by 46
- 2019Mining Discourse Markers for Unsupervised Sentence Representation Learningcited by 34
- 2019DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusioncited by 29
Built on by
Citing papers per year: 2023: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI
- 2023SYNDICOM: Improving Conversational Commonsense with Error-Injection and Natural Language Feedback
- 2023Advancing Transformer's Capabilities in Commonsense Reasoning
- 2023Commonsense Reasoning for Conversational AI: A Survey of the State of the Art
- 2024Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models
- 2026Abductive Reasoning with Probabilistic Commonsense
- 2023CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks
- 2022A Theoretically Grounded Benchmark for Evaluating Machine Commonsense