# Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition

arXiv: https://arxiv.org/abs/2607.08374 · HTML: https://mlsanity.com/paper/2607.08374/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 57 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [Evaluation of OpenAI o1: Opportunities and Challenges of AGI](https://mlsanity.com/paper/2409.18486/) (2024)
- [Is ChatGPT a Good Personality Recognizer? A Preliminary Study](https://mlsanity.com/paper/2307.03952/) (2023)
- [LLMvsSmall Model? Large Language Model Based Text Augmentation Enhanced Personality Detection Model](https://mlsanity.com/paper/2403.07581/) (2024)
- [A Survey on Personality-Aware Recommendation Systems](https://mlsanity.com/paper/2101.12153/) (2021)
- [Orders Are Unwanted: Dynamic Deep Graph Convolutional Network for Personality Detection](https://mlsanity.com/paper/2212.01515/) (2022)
- [Psycholinguistic Tripartite Graph Network for Personality Detection](https://mlsanity.com/paper/2106.04963/) (2021)
- [Pushing on Personality Detection from Verbal Behavior: A Transformer Meets Text Contours of Psycholinguistic Features](https://mlsanity.com/paper/2204.04629/) (2022)
- [Text-Based Automatic Personality Prediction Using KGrAt-Net; A Knowledge Graph Attention Network Classifier](https://mlsanity.com/paper/2205.13780/) (2022)
- [EERPD: Leveraging Emotion and Emotion Regulation for Improving Personality Detection](https://mlsanity.com/paper/2406.16079/) (2024)
- [Enhancing Textual Personality Detection toward Social Media: Integrating Long-term and Short-term Perspectives](https://mlsanity.com/paper/2404.15067/) (2024)
- [Prompting-in-a-Series: Psychology-Informed Contents and Embeddings for Personality Recognition With Decoder-Only Models](https://mlsanity.com/paper/2512.06991/) (2025)
- [Big-Five, MPTI, Eysenck or HEXACO: The Ideal Personality Model for Personality-aware Recommendation Systems](https://mlsanity.com/paper/2106.03060/) (2021)
- [Exploring Personality-Driven Personalization in XAI: Enhancing User Trust in Gameplay](https://mlsanity.com/paper/2408.04778/) (2024)
- [Cross-Lingual Attention Distillation with Personality-Informed Generative Augmentation for Multilingual Personality Recognition](https://mlsanity.com/paper/2604.08851/) (2026)

## Abstract (arXiv)

Personality recognition has traditionally been constrained by theory-dependent formulations, where models are trained to fit predefined psychological taxonomies rather than uncovering shared underlying behavioral structure. This limits generalization, as personality itself is better understood as theory-invariant, while existing annotations reflect only partial and sometimes inconsistent views of the same latent traits. In this work, we introduce JAM ((J)udge for (A)daptive (M)etric-Alignment), a theory-agnostic framework that shifts learning from adapting to predefined personality theories toward discovering unified latent pseudo-facets that capture shared psychological structure. Rather than constraining the model to any personality taxonomy during training or inference, the framework learns generalizable psychological representations and can infer an individual's latent psychological profile directly from the textual samples, without requiring theory-specific labels. JAM achieves this through an Attention-Pooled Graph Prototypical Network that learns structured representations via clustering in embedding space, together with a Cross-Theory Harmonization (CTH) approach that integrates (i) Human-Guided Linkage and (ii) Machine-Induced Consensus to unify heterogeneous datasets without relying on predefined labels. To further improve robustness and data quality, we incorporate an LLM-as-a-Judge mechanism operating in two configurations, (i) LLM-before-the-loop and (ii) LLM-in-the-loop which identifies ambiguous samples to guide adaptive metric learning. Experiments show that JAM improves cross-framework generalization and performance, establishing a strong step toward theory-agnostic personality inference and supporting low-resource personality theories. The related code repository, model weights, and artifacts are available at https://research.jingjietan.com/JAM