arXiv subjects

Yindi Liu

Publications and source records attributed to Yindi Liu.

4 recordsLinked to original sources

arXiv2025

Visual Orientalism in the AI Era: From West-East Binaries to English-Language Centrism

Text-to-image AI models systematically encode geopolitical bias through visual representation. Drawing on Said's Orientalism and framing theory, we introduce Visual Orientalism - the dual standard whereby AI depicts Western nations through political-modern symbols while portraying Eastern nations through cultural-traditional symbols. Analyzing 396 AI-generated images across 12 countries and 3 models, we reveal an evolution: Visual Orientalism has shifted from traditional West-versus-East binaries to English-language centrism, where only English-speaking core countries (USA and UK) receive political representation while all other nations - including European powers - face cultural exoticization. This algorithmic reconfiguration operates through automated framing mechanisms shaped by English-language training data dominance. Our findings demonstrate how AI systems function as agents of cultural representation that perpetuate and intensify historical power asymmetries. Addressing Visual Orientalism requires rethinking of algorithmic governance and the geopolitical structures embedded in AI training data.

cs.CY↗

arXiv2025

A Hierarchical Error Framework for Reliable Automated Coding in Communication Research: Applications to Health and Political Communication

Automated content analysis increasingly supports communication research, yet scaling manual coding into computational pipelines raises concerns about measurement reliability and validity. We introduce a Hierarchical Error Correction (HEC) framework that treats model failures as layered measurement errors (knowledge gaps, reasoning limitations, and complexity constraints) and targets the layers that most affect inference. The framework implements a three-phase methodology: systematic error profiling across hierarchical layers, targeted intervention design matched to dominant error sources, and rigorous validation with statistical testing. Evaluating HEC across health communication (medical specialty classification) and political communication (bias detection), and legal tasks, we validate the approach with five diverse large language models. Results show average accuracy gains of 11.2 percentage points (p < .001, McNemar's test) and stable conclusions via reduced systematic misclassification. Cross-model validation demonstrates consistent improvements (range: +6.8 to +14.6pp), with effectiveness concentrated in moderate-to-high baseline tasks (50-85% accuracy). A boundary study reveals diminished returns in very high-baseline (>85%) or precision-matching tasks, establishing applicability limits. We map layered errors to threats to construct and criterion validity and provide a transparent, measurement-first blueprint for diagnosing error profiles, selecting targeted interventions, and reporting reliability/validity evidence alongside accuracy. This applies to automated coding across communication research and the broader social sciences.

cs.CL↗

arXiv2025

Automated Quality Assessment for LLM-Based Complex Qualitative Coding: A Confidence-Diversity Framework

Computational social science lacks a scalable and reliable mechanism to assure quality for AI-assisted qualitative coding when tasks demand domain expertise and long-text reasoning, and traditional double-coding is prohibitively costly at scale. We develop and validate a dual-signal quality assessment framework that combines model confidence with inter-model consensus (external entropy) and evaluate it across legal reasoning (390 Supreme Court cases), political analysis (645 hyperpartisan articles), and medical classification (1,000 clinical transcripts). External entropy is consistently negatively associated with accuracy (r = -0.179 to -0.273, p < 0.001), while confidence is positively associated in two domains (r = 0.104 to 0.429). Weight optimization improves over single-signal baselines by 6.6-113.7% and transfers across domains (100% success), and an intelligent triage protocol reduces manual verification effort by 44.6% while maintaining quality. The framework offers a principled, domain-agnostic quality assurance mechanism that scales qualitative coding without extensive double-coding, provides actionable guidance for sampling and verification, and enables larger and more diverse corpora to be analyzed with maintained rigor.

cs.CY↗

arXiv2025

A Confidence-Diversity Framework for Calibrating AI Judgement in Accessible Qualitative Coding Tasks

LLMs enable qualitative coding at large scale, but assessing reliability remains challenging where human experts seldom agree. We investigate confidence-diversity calibration as a quality assessment framework for accessible coding tasks where LLMs already demonstrate strong performance but exhibit overconfidence. Analysing 5,680 coding decisions from eight state-of-the-art LLMs across ten categories, we find that mean self-confidence tracks inter-model agreement closely (Pearson r=0.82). Adding model diversity quantified as normalised Shannon entropy produces a dual signal explaining agreement almost completely (R-squared=0.979), though this high predictive power likely reflects task simplicity for current LLMs. The framework enables a three-tier workflow auto-accepting 35 percent of segments with less than 5 percent error, cutting manual effort by 65 percent. Cross-domain validation confirms transferability (kappa improvements of 0.20 to 0.78). While establishing a methodological foundation for AI judgement calibration, the true potential likely lies in more challenging scenarios where LLMs may demonstrate comparative advantages over human cognitive limitations.

cs.LG↗