arXiv subjects

Zehao Zhong

Publications and source records attributed to Zehao Zhong.

5 recordsLinked to original sources

arXiv2026

A Survey of Large Language Models for Perception and Measurement of Human Psychology

Against the backdrop of the rapid advancement of Large Language Models (LLMs), their application in the field of psychology has garnered significant academic attention. A central issue is whether LLMs possess the capability to accurately perceive and measure complex, latent human psychological constructs, such as personality, emotions, and cognitive states. This paper provides a systematic review focused on the use of LLMs as instruments for human psychological measurement. To organize this domain, we propose a comprehensive analytical framework structured around three critical dimensions: Theoretical Plausibility (why measurement might be possible), Measurement Methodology (how to measure), and Application Effectiveness (what has been measured). We first explore the theoretical foundations supporting LLM-based measurement, examining the debate on their emergent cognitive properties from a psychometric perspective. Next, we systematically analyze existing measurement paradigms, categorizing them into active conversational assessment, passive natural language analysis, and multimodal fusion. Subsequently, we review the practical effectiveness and limitations of LLMs in core application areas, including personality trait assessment and mental health evaluation. Distinct from prior reviews focusing on general applications or the ``psychology'' of LLMs themselves, this paper centers on the psychometric properties of LLMs as measurement tools.

cs.CY↗

arXiv2026

X-PCR: A Benchmark for Cross-modality Progressive Clinical Reasoning in Ophthalmic Diagnosis

Despite significant progress in Multi-modal Large Language Models (MLLMs), their clinical reasoning capacity for multi-modal diagnosis remains largely unexamined. Current benchmarks, mostly single-modality data, can't evaluate progressive reasoning and cross-modal integration essential for clinical practice. We introduce the Cross-Modality Progressive Clinical Reasoning (X-PCR) benchmark, the first comprehensive evaluation of MLLMs through a complete ophthalmology diagnostic workflow, with two reasoning tasks: 1) a six-stage progressive reasoning chain spanning image quality assessment to clinical decision-making, and 2) a cross-modality reasoning task integrating six imaging modalities. The benchmark comprises 26,415 images and 177,868 expert-verified VQA pairs curated from 51 public datasets, covering 52 ophthalmic diseases. Evaluation of 21 MLLMs reveals critical gaps in progressive reasoning and cross-modal integration. Dataset and code: https://github.com/CVI-SZU/X-PCR.

cs.CV↗

arXiv2025

EyePCR: A Comprehensive Benchmark for Fine-Grained Perception, Knowledge Comprehension and Clinical Reasoning in Ophthalmic Surgery

MLLMs (Multimodal Large Language Models) have showcased remarkable capabilities, but their performance in high-stakes, domain-specific scenarios like surgical settings, remains largely under-explored. To address this gap, we develop \textbf{EyePCR}, a large-scale benchmark for ophthalmic surgery analysis, grounded in structured clinical knowledge to evaluate cognition across \textit{Perception}, \textit{Comprehension} and \textit{Reasoning}. EyePCR offers a richly annotated corpus with more than 210k VQAs, which cover 1048 fine-grained attributes for multi-view perception, medical knowledge graph of more than 25k triplets for comprehension, and four clinically grounded reasoning tasks. The rich annotations facilitate in-depth cognitive analysis, simulating how surgeons perceive visual cues and combine them with domain knowledge to make decisions, thus greatly improving models' cognitive ability. In particular, \textbf{EyePCR-MLLM}, a domain-adapted variant of Qwen2.5-VL-7B, achieves the highest accuracy on MCQs for \textit{Perception} among compared models and outperforms open-source models in \textit{Comprehension} and \textit{Reasoning}, rivalling commercial models like GPT-4.1. EyePCR reveals the limitations of existing MLLMs in surgical cognition and lays the foundation for benchmarking and enhancing clinical reliability of surgical video understanding models.

cs.CV↗

arXiv2024

Kinematical small-scale fluctuations do not affect the measurement of the dynamical mass of galaxies

The stellar kinematics of low-mass galaxies are usually observed to be very unsmooth with significant kinematical fluctuations in small scales, which cannot be consistent with the projected centrosymmetric stellar kinematics obtained from commonly used dynamical models. In this work, we aim to test whether the high degree of kinematical fluctuations affects the dynamical mass estimate of galaxies. We use the asymmetry parameter $η$ obtained from the $180^{\circ}$ rotation self-subtraction of stellar kinematics of galaxies to quantify the degree of kinematical small-scale fluctuations. We use TNG50 numerical simulation to construct a large sample of mock galaxies with known total masses, and then obtained the virial dynamical mass estimator of these mock galaxies. We find that the dynamical masses within three-dimensional $R_{\rm e}$ to the mock galaxy centres are overall averagely accurate within around 0.1 dex under the symmetric assumption, while $R_{\rm e}$ means the projected circularized half-stellar mass radius in this work. We study the local virial mass estimation bias for mock galaxies of different $η$. The maximum bias difference of two $η$ bins is around 0.16 dex, which with other local biases may help apply the observational virial mass estimators obtained from massive galaxies to other types of galaxies. We find that the Spearman's $ρ$ of $η$ with the intrinsic mass estimation deviations is near zero if the local bias is eliminated properly. The results indicate that even for low-mass galaxies, the existence of high degree of kinematical small-scale fluctuations does not affect the measurement of the dynamical mass of galaxies.

astro-ph.GA↗

arXiv2023

Preliminary Exploration of Areal Density of Angular Momentum for Spiral Galaxies

The specific angular momenta ($j_t$) of stars, baryons as a whole and dark matter haloes contain clues of vital importance about how galaxies form and evolve. Using a sample of 70 spiral galaxies, we perform a preliminary analysis of $j_t$, and introduce a new quantity, e.g., areal density of angular momentum (ADAM) ($j_t~M_\star/4R_d^2$) as an indication for the existence of jet in spiral galaxies. The percentage of spiral galaxies having jet(s) shows strong correlation with the ADAM, although the present sample is incomplete.

astro-ph.GA↗