Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.06991 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914185936371712 |
|---|---|
| author | Tan, Jing Jie Kwan, Ban-Hoe Ng, Danny Wee-Kiat Hum, Yan-Chai Mokraoui, Anissa Lo, Shih-Yu |
| author_facet | Tan, Jing Jie Kwan, Ban-Hoe Ng, Danny Wee-Kiat Hum, Yan-Chai Mokraoui, Anissa Lo, Shih-Yu |
| contents | Large Language Models (LLMs) have demonstrated remarkable capabilities across various natural language processing tasks. This research introduces a novel "Prompting-in-a-Series" algorithm, termed PICEPR (Psychology-Informed Contents Embeddings for Personality Recognition), featuring two pipelines: (a) Contents and (b) Embeddings. The approach demonstrates how a modularised decoder-only LLM can summarize or generate content, which can aid in classifying or enhancing personality recognition functions as a personality feature extractor and a generator for personality-rich content. We conducted various experiments to provide evidence to justify the rationale behind the PICEPR algorithm. Meanwhile, we also explored closed-source models such as \textit{gpt4o} from OpenAI and \textit{gemini} from Google, along with open-source models like \textit{mistral} from Mistral AI, to compare the quality of the generated content. The PICEPR algorithm has achieved a new state-of-the-art performance for personality recognition by 5-15\% improvement. The work repository and models' weight can be found at https://research.jingjietan.com/?q=PICEPR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06991 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prompting-in-a-Series: Psychology-Informed Contents and Embeddings for Personality Recognition With Decoder-Only Models Tan, Jing Jie Kwan, Ban-Hoe Ng, Danny Wee-Kiat Hum, Yan-Chai Mokraoui, Anissa Lo, Shih-Yu Computation and Language Artificial Intelligence Large Language Models (LLMs) have demonstrated remarkable capabilities across various natural language processing tasks. This research introduces a novel "Prompting-in-a-Series" algorithm, termed PICEPR (Psychology-Informed Contents Embeddings for Personality Recognition), featuring two pipelines: (a) Contents and (b) Embeddings. The approach demonstrates how a modularised decoder-only LLM can summarize or generate content, which can aid in classifying or enhancing personality recognition functions as a personality feature extractor and a generator for personality-rich content. We conducted various experiments to provide evidence to justify the rationale behind the PICEPR algorithm. Meanwhile, we also explored closed-source models such as \textit{gpt4o} from OpenAI and \textit{gemini} from Google, along with open-source models like \textit{mistral} from Mistral AI, to compare the quality of the generated content. The PICEPR algorithm has achieved a new state-of-the-art performance for personality recognition by 5-15\% improvement. The work repository and models' weight can be found at https://research.jingjietan.com/?q=PICEPR. |
| title | Prompting-in-a-Series: Psychology-Informed Contents and Embeddings for Personality Recognition With Decoder-Only Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2512.06991 |