Towards Explaining Subjective Ground of Individuals on Social Media
Not on the map. Why?
Abstract (arXiv)
Large-scale language models have been reducing the gap between machines and humans in understanding the real world, yet understanding an individual's theory of mind and behavior from text is far from being resolved. This research proposes a neural model -- Subjective Ground Attention -- that learns subjective grounds of individuals and accounts for their judgments on situations of others posted on social media. Using simple attention modules as well as taking one's previous activities into consideration, we empirically show that our model provides human-readable explanations of an individual's subjective preference in judging social situations. We further qualitatively evaluate the explanations generated by the model and claim that our model learns an individual's subjective orientation towards abstract moral concepts
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 36 references that are in the map. First posted on arXiv 18 Nov 2022.
Builds on
20 of 36 references.
References · 20
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
- 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
- 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
- 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
- 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
- 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
8 more
- 2018Explainable Prediction of Medical Codes from Clinical Textcited by 231
- 2017Thinking Fast and Slow: Optimization Decomposition Across Timescalescited by 60
- 2018Framing and Agenda-setting in Russian News: a Computational Analysis of Intricate Political Strategiescited by 47
- 2019Investigating Robustness and Interpretability of Link Prediction via Adversarial Modificationscited by 25
- 2018Interpreting Neural Networks With Nearest Neighborscited by 18
- 2017An Interpretable Knowledge Transfer Model for Knowledge Base Completioncited by 17
- 2016Interpreting Neural Networks to Improve Politeness Comprehensioncited by 12
- 2019Interpretable Question Answering on Knowledge Bases and Textcited by 8
Built on by
Citing papers per year: 2025: 2.
2 papers.