Imagen de Portada

The fragility of "cultural tendencies" in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sun, Kun, Wang, Rong
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs
por: Wang, Rong, et al.
Publicado: (2024)

Systematic Framework of Application Methods for Large Language Models in Language Sciences
por: Sun, Kun, et al.
Publicado: (2025)

Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach
por: Sun, Kun, et al.
Publicado: (2024)

Differential contributions of machine learning and statistical analysis to language and cognitive sciences
por: Sun, Kun, et al.
Publicado: (2024)

Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction
por: Sun, Qi, et al.
Publicado: (2024)

A Novel Dependency Framework for Enhancing Discourse Data Analysis
por: Sun, Kun, et al.
Publicado: (2024)

Textual Similarity as a Key Metric in Machine Translation Quality Estimation
por: Sun, Kun, et al.
Publicado: (2024)

Computational Sentence-level Metrics Predicting Human Sentence Comprehension
por: Sun, Kun, et al.
Publicado: (2024)

Automatic Essay Multi-dimensional Scoring with Fine-tuning and Multiple Regression
por: Sun, Kun, et al.
Publicado: (2024)

Continuous Output Personality Detection Models via Mixed Strategy Training
por: Wang, Rong, et al.
Publicado: (2024)

Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs
por: Sun, Tianyu, et al.
Publicado: (2025)

TIMIT Speaker Profiling: A Comparison of Multi-task learning and Single-task learning Approaches
por: Wang, Rong, et al.
Publicado: (2024)

Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs
por: Tan, Jiejun, et al.
Publicado: (2024)

Benchmarking LLMs' Swarm intelligence
por: Ruan, Kai, et al.
Publicado: (2025)

Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs
por: Liu, Chengyuan, et al.
Publicado: (2024)

Evaluating the performance and fragility of large language models on the self-assessment for neurological surgeons
por: Vishwanath, Krithik, et al.
Publicado: (2025)

More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs
por: Liu, Chengyuan, et al.
Publicado: (2024)

HearSay Benchmark: Do Audio LLMs Leak What They Hear?
por: Wang, Jin, et al.
Publicado: (2026)

Large language models show fragile cognitive reasoning about human emotions
por: Bhattacharyya, Sree, et al.
Publicado: (2025)

Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs
por: Wei, Zeyu, et al.
Publicado: (2025)

Enhancing LLMs via High-Knowledge Data Selection
por: Duan, Feiyu, et al.
Publicado: (2025)

MIST: Towards Multi-dimensional Implicit BiaS Evaluation of LLMs for Theory of Mind
por: Li, Yanlin, et al.
Publicado: (2025)

CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns
por: Zhou, Zhenhong, et al.
Publicado: (2026)

On the Role of Discreteness in Diffusion LLMs
por: Jin, Ziqi, et al.
Publicado: (2025)

Length Controlled Generation for Black-box LLMs
por: Gu, Yuxuan, et al.
Publicado: (2024)

Attention-aware semantic relevance predicting Chinese sentence reading
por: Sun, Kun
Publicado: (2024)

Effective Distillation of Table-based Reasoning Ability from LLMs
por: Yang, Bohao, et al.
Publicado: (2023)

Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judge
por: Cai, Yunna, et al.
Publicado: (2025)

Purple-teaming LLMs with Adversarial Defender Training
por: Zhou, Jingyan, et al.
Publicado: (2024)

Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment
por: Chen, Zhipeng, et al.
Publicado: (2024)

From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs
por: Ni, Jiliang, et al.
Publicado: (2025)

Academically intelligent LLMs are not necessarily socially intelligent
por: Xu, Ruoxi, et al.
Publicado: (2024)

LLMs + Persona-Plug = Personalized LLMs
por: Liu, Jiongnan, et al.
Publicado: (2024)

Progressing beyond Art Masterpieces or Touristic Clichés: how to assess your LLMs for cultural alignment?
por: Branco, António, et al.
Publicado: (2026)

Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation
por: Liu, Geng, et al.
Publicado: (2026)

Designing LLMs for cultural sensitivity: Evidence from English-Japanese translation
por: Tenzer, Helene, et al.
Publicado: (2025)

Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs
por: Sun, Chenxi, et al.
Publicado: (2024)

Generative Pseudo-Labeling for Pre-Ranking with LLMs
por: Bi, Junyu, et al.
Publicado: (2026)

TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice
por: Hu, Gang, et al.
Publicado: (2026)

RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward
por: Wang, Zongsheng, et al.
Publicado: (2025)