TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/CICERO: A Dataset for Contextualized Commonsense Inference...

CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues

Deepanway Ghosal, Siqi Shen, Navonil Majumder, Rada Mihalcea, Soujanya Poria

2022-03-25ACL 2022 5Answer SelectionAnswer Generation
PaperPDFCode(official)

Abstract

This paper addresses the problem of dialogue reasoning with contextualized commonsense inference. We curate CICERO, a dataset of dyadic conversations with five types of utterance-level reasoning-based inferences: cause, subsequent event, prerequisite, motivation, and emotional reaction. The dataset contains 53,105 of such inferences from 5,672 dialogues. We use this dataset to solve relevant generative and discriminative tasks: generation of cause and subsequent event; generation of prerequisite, motivation, and listener's emotional reaction; and selection of plausible alternatives. Our results ascertain the value of such dialogue-centric commonsense knowledge datasets. It is our hope that CICERO will open new research avenues into commonsense-based dialogue reasoning.

Results

TaskDatasetMetricValueModel
Question AnsweringCICEROExact Match77.68T5-large
Question AnsweringCICEROExact Match77.51Unified QA
Question AnsweringCICEROROUGE0.298T5-large pre-trained on GLUCOSE
Question AnsweringCICEROROUGE0.2946T5-large
Question AnsweringCICEROROUGE0.2878T5-large pre-trained on COMET
Question AnsweringCICEROROUGE0.2837BART
Natural Language InferenceCICEROROUGE0.298T5-large pre-trained on GLUCOSE
Natural Language InferenceCICEROROUGE0.2947T5-large

Related Papers

Small Encoders Can Rival Large Decoders in Detecting Groundedness2025-06-26GEMeX-ThinkVG: Towards Thinking with Visual Grounding in Medical VQA via Reinforcement Learning2025-06-22RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge2025-06-17RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition2025-06-17FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design2025-06-16CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making2025-06-15TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning2025-06-12Neural at ArchEHR-QA 2025: Agentic Prompt Optimization for Evidence-Grounded Clinical Question Answering2025-06-12