Amir Homayounirad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Amir Homayounirad has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Luciano Cavalcante Siebert
Delft University of Technology The Netherlands
3 shared publications - Catholijn M. Jonker
INSY, Delft University of Technology, Delft, Netherlands and LIACS, Leiden University, Leiden, Netherlands
2 shared publications - Enrico Liscio
Delft University of Technology The Netherlands
2 shared publications Tong Wang
Delft University of Technology The Netherlands
2 shared publications- Rithik Appachi Senthilkumar
Delft University of Technology
1 shared publication
Latest Publications
- Open Access
Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying subjectivity in recognizing the human values that motivate arguments. We evaluate two main approaches: inferring subjectivity through value prediction vs. directly identifying subjectivity. Our experiments show that direct subjectivity identification significantly improves the model performance of flagging subjective arguments. Furthermore, combining contrastive loss with binary cross-entropy loss does not improve performance but reduces the dependency on per-label subjectivity. Our proposed methods can help identify arguments that individuals may interpret differently, fostering a more nuanced annotation process.
Open AccessWill Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying subjectivity in recognizing the human values that motivate arguments. We evaluate two main approaches: inferring subjectivity through value prediction vs. directly identifying subjectivity. Our experiments show that direct subjectivity identification significantly improves the model performance of flagging subjective arguments. Furthermore, combining contrastive loss with binary cross-entropy loss does not improve performance but reduces the dependency on per-label subjectivity. Our proposed methods can help identify arguments that individuals may interpret differently, fostering a more nuanced annotation process.
- 21 March 2025
- Published by Springer Nature
- p. 87-103
Leveraging Large Language Models to Identify the Values Behind Arguments
- 21 March 2025
- Published by Springer Nature
- p. 87-103
Leveraging Large Language Models to Identify the Values Behind Arguments
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 15237-15252
Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
Amir Homayounirad, Enrico Liscio, Tong Wang, Catholijn M Jonker, Luciano Cavalcante Siebert. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 15237-15252
Open AccessWill Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
Amir Homayounirad, Enrico Liscio, Tong Wang, Catholijn M Jonker, Luciano Cavalcante Siebert. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
- 22 June 2023
- Published by IOS Press
- p. 483-495
Designing the Built Environment Through Hybrid Intelligence
There is a lack of an intelligent platform that supports continuous deliberation and captures diverse views and stakeholders’ values during the architectural design process in the early stages. Using hybrid intelligence, this study proposes a method that integrates value, and design pattern theories, to support deliberation during the design process. Three steps comprise the method: eliciting value, extracting design patterns, and designing through deliberation with AI agents using natural language processing through hybrid intelligence. The final set of design patterns reflects the participants’ values and ideas, facilitating informed consensus and collaboration between stakeholders supported by AI agents. By integrating diverse perspectives into the loop through continuous deliberation, the proposed method incorporates stakeholders’ value for extracting design patterns that address primary design goals and challenges such as energy transition in the built environment.
- 22 June 2023
- Published by IOS Press
- p. 483-495
Open AccessDesigning the Built Environment Through Hybrid Intelligence
There is a lack of an intelligent platform that supports continuous deliberation and captures diverse views and stakeholders’ values during the architectural design process in the early stages. Using hybrid intelligence, this study proposes a method that integrates value, and design pattern theories, to support deliberation during the design process. Three steps comprise the method: eliciting value, extracting design patterns, and designing through deliberation with AI agents using natural language processing through hybrid intelligence. The final set of design patterns reflects the participants’ values and ideas, facilitating informed consensus and collaboration between stakeholders supported by AI agents. By integrating diverse perspectives into the loop through continuous deliberation, the proposed method incorporates stakeholders’ value for extracting design patterns that address primary design goals and challenges such as energy transition in the built environment.