ACL Findings2022
Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problem
Qiang Zhang, Jason Naradowsky, Yusuke Miyao
Abstract
We introduce the task of implicit offensive text detection in dialogues, where a statement may have either an offensive or non-offensive interpretation, depending on the listener and context. We argue that reasoning is crucial for understanding this broader class of offensive utterances and release SLIGHT, a dataset to support research on this task. Experiments using the data show that state-of-the-art methods of offense detection perform poorly when asked to detect implicitly offensive statements, achieving only ∼11% accuracy.
In contrast to existing offensive text detection datasets, SLIGHT features human-annotated chains of reasoning which describe the mental process by which an offensive interpretation can be reached from each ambiguous statement. We explore the potential for a multi-hop reasoning approach by utilizing existing entailment models to score the probability of these chains and show that even naive reasoning models can yield improved performance in most situations. Furthermore, analysis of the chains provides insight into the human interpretation process and emphasizes the importance of incorporating additional commonsense knowledge.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on7
- Deberta: decoding-Enhanced Bert with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu ChenICLR 2021 · 3,729 citations
- TweetEval: Unified Benchmark and Comparative Evaluation for Tweet ClassificationFrancesco Barbieri, José Camacho-Collados, Luis Espinosa Anke, Leonardo NevesEMNLP Findings 2020 · 720 citations
- GeDi: Generative Discriminator Guided Sequence GenerationBen Krause, Akhilesh Deepak Gotmare, Bryan McCann, Nitish Shirish Keskar et al.EMNLP Findings 2021 · 219 citations
- Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their ConsequencesDenis Emelin, Ronan Le Bras, Jena D. Hwang, Maxwell Forbes et al.EMNLP 2021 · 83 citations
- Debiasing knowledge graph embeddingsJoseph Fisher, Arpit Mittal, Dave Palfrey, Christos ChristodoulopoulosEMNLP 2020 · 40 citations
Related papers
- Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social RelationshipsDavid Jurgens, Agrima Seth, Jackson Sargent, Athena Aghighi et al.ACL 2023 · 4 citations
- GRICE: A Grammar-based Dataset for Recovering Implicature and Conversational rEasoningZilong Zheng, Shuwen Qiu, Lifeng Fan, Yixin Zhu et al.ACL Findings 2021 · 12 citations
- Leveraging Conflicts in Social Media Posts: Unintended Offense DatasetChe-Wei Tsai, Yen-Hao Huang, Tsu-Keng Liao, Didier Estrada et al.EMNLP 2024
- Entailed Between the Lines: Incorporating Implication into NLIShreya Havaldar, Hamidreza Alvari, John Palowitch, Mohammad Javad Hosseini et al.ACL 2025
- VAGUE: Visual Contexts Clarify Ambiguous ExpressionsHeejeong Nam, Jinwoo Ahn, Keummin Ka, Jiwan Chung et al.ICCV 2025 · 1 citation
