Entity · product

JAM (Judge for Adaptive Metric-Alignment)

productactiveprovisionaljam-judge-for-adaptive-metric-alignment--f52ec01e·1 events·first seen 2h ago

Aliases: JAM (Judge for Adaptive Metric-Alignment)

Co-occurring entities

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

More like this (12)

MedAlign Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition SAM Audio Judge mJudge When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability misalignment detection AI alignment LLM-judge scoring G-IdiomAlign human alignment benchmarks (perceptual similarity, gloss, robustness, shape-texture)Janus: A Benchmark for Goal-Conditioned Information Distortion in LLMs AGC-Judge

Recent events (1)

4arXiv · cs.CL·2h ago·source ↗

JAM: LLM-as-a-Judge framework for theory-agnostic personality recognition via prototypical networks

Researchers introduce JAM (Judge for Adaptive Metric-Alignment), a framework for personality recognition that avoids dependence on predefined psychological taxonomies like Big Five or MBTI. The system uses an Attention-Pooled Graph Prototypical Network with a Cross-Theory Harmonization approach to unify heterogeneous personality datasets, and incorporates an LLM-as-a-Judge mechanism in two configurations to identify ambiguous training samples and guide metric learning. Experiments show improved cross-framework generalization, with the approach enabling inference of latent psychological profiles from text without theory-specific labels.

Evaluation and Benchmarking Cross-Theory Harmonization Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition JAM (Judge for Adaptive Metric-Alignment)