Papers by Ayoub Bagheri
On Text-based Personality Computing: Challenges and Future Directions (2023.findings-acl)
Copied to clipboard
Qixiang Fang, Anastasia Giachanou, Ayoub Bagheri, Laura Boeschoten, Erik-Jan van Kesteren, Mahdi Shafiee Kamalabad, Daniel Oberski
| Challenge: | Text-based personality computing (TPC) is a popular alternative to self-report questionnaires. |
| Approach: | They propose 15 challenges that are relevant to NLP research . they propose to combine perspectives from both NLP and social sciences . |
| Outcome: | The proposed approach is based on text-based personality computing (TPC) the proposed approach can be used to improve the quality of personality-based research. |
LAD: LoRA-Adapted Diffusion (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Autoregressive models dominate text generation but suffer from left-to-right decoding constraints that limit efficiency and bidirectional reasoning. |
| Approach: | They propose a framework for non-autoregressive generation that adapts LLaMA models for iterative, bidirectional sequence refinement using LoRA adapters. |
| Outcome: | The proposed framework adapts LLaMA models for iterative, bidirectional sequence refinement using LoRA adapters. |