Fine-Tuned Multi-Agent Framework for Detecting OCEAN in Life Narratives
Quick Answer
The proposed fine-tuned multi-agent framework enhances OCEAN personality trait detection in life narratives by utilizing sub-agents with varied perspectives and a judge LLM for aggregation.
Quick Take
The proposed fine-tuned framework enhances OCEAN personality trait detection in life narratives by utilizing sub-agents with varied perspectives and a judge LLM for aggregation. This method addresses biases from large language models and demonstrates improved inference quality through quantitative and qualitative evaluations.
Key Points
- Framework employs masked language modeling and psychometric supervision for trait detection.
- Sub-agents adopt high, low, or neutral perspectives to mitigate biases.
- Judge LLM aggregates outputs for final trait predictions, enhancing interpretability.
- Evaluated on life narrative datasets with quantitative and qualitative experiments.
- Offers a scalable method for text-based personality inference.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Accurately assessing personality from text is challenging because traits are latent, context-dependent, and often subtly expressed across long narratives. Large language models (LLMs) offer new opportunities by processing extensive textual contexts, but pretraining of these models can induce latent "personality-like" biases, making single-model inferences inconsistent. We propose a fine-tuned multi-agent framework for detecting OCEAN personality traits, in which sub-agents are conditioned to adopt high, low, or neutral perspectives for each trait through masked language modeling (MLM) and psychometric supervision. A judge LLM aggregates and compares sub-agent outputs to generate final trait predictions, capturing multiple complementary perspectives while mitigating individual model biases. We evaluate the framework on life narrative dataset through quantitative and qualitative experiments, including baselines, ablations, and inference quality analyses. Our approach offers a scalable and interpretable method for text-based personality inference, highlighting the benefits of multi-agent reasoning grounded in psychometric supervision.
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2607.12215 [cs.CL] |
| (or arXiv:2607.12215v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.12215 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rasiq Hussain [view email]
[v1]
Mon, 13 Jul 2026 23:26:16 UTC (667 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI
The study evaluates three NLP approaches—Named Entity Recognition, Keyword Extraction, and Topic Modelling—using the Their Finest Hour Online Archive to automate keyword extraction from crowdsourced WWII collections. Findings suggest that while NLP methods show promise, no single approach is sufficient, and ethical considerations in automated keyword extraction are crucial for responsible stewardship.