mlsanityData to 14 Oct 2026

Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings

arXiv 2610.16050 ↗First posted 12 Oct 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Personality assessment from asynchronous video interviews (AVIs) plays a crucial role in recruitment by enabling standardized and behaviorally grounded evaluation for job applicants. However, most of the previous works are confined to a single interview protocol. Independently collected protocols differ in question sets and question-trait mapping. Thus, the human-rated evidence from one protocol cannot be used directly under another. To address this limitation, we propose the Cross-protocol Evidence-grounded Personality Assessment (CEPA) framework, which aligns behavioral representations across interview protocols. CEPA addresses protocol heterogeneity by projecting source behavioral records into the target protocol's construct-oriented representation space. It retrieves behaviorally relevant and personality-complementary human-rated exemplars to ground an ensemble of LLM raters, which enables behavior-to-personality associations without target-specific supervision. In cross-protocol experiments, CEPA reduces average mean squared error (MSE) by 43.8% (Forward) and 17.0% (Reverse) relative to the strongest baseline. Our empirical experiments show that human-rated evidence from one protocol can support personality assessment under another without target-specific supervision or retraining.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 47 references that are in the map. First posted on arXiv 12 Oct 2026.

Builds on

21 of 47 references.

References · 21

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  9. 2025Gemma 3 Technical Reportcited by 1,824
  10. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  11. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  12. 2022Diverse Demonstrations Improve In-context Compositional Generalizationcited by 139
9 more
  1. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answeringcited by 127
  2. 2023Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimationcited by 29
  3. 2023Large Language Models Can Infer Psychological Dispositions of Social Media Userscited by 29
  4. 2023Is ChatGPT a Good Personality Recognizer? A Preliminary Studycited by 26
  5. 2025Fun-Audio-Chat Technical Reportcited by 19
  6. 2025Less but Better: Parameter-Efficient Fine-Tuning of Large Language Models for Personality Detectioncited by 7
  7. 2026DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generationcited by 5
  8. 2024Personality Analysis from Online Short Video Platforms with Multi-domain Adaptationcited by 1
  9. 2026LLM-based Multimodal Personality Recognition via Facial Action Unit-Text Semantic Fusioncited by 1

Built on by

Not cited yet.