Imagen de Portada

Stress-Testing Model Specs Reveals Character Differences among Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Jifan, Sleight, Henry, Peng, Andi, Schulman, John, Durmus, Esin
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
por: Guo, Shiyuan, et al.
Publicado: (2025)

Looking Inward: Language Models Can Learn About Themselves by Introspection
por: Binder, Felix J, et al.
Publicado: (2024)

From Language Models over Tokens to Language Models over Characters
por: Vieira, Tim, et al.
Publicado: (2024)

DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
por: Li, Guanghao, et al.
Publicado: (2025)

Unsupervised Elicitation of Language Models
por: Wen, Jiaxin, et al.
Publicado: (2025)

SpecFuse: Ensembling Large Language Models via Next-Segment Prediction
por: Lv, Bo, et al.
Publicado: (2024)

Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
por: Huang, Saffron, et al.
Publicado: (2025)

WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models
por: Tu, Shangqing, et al.
Publicado: (2023)

DynaSpec: Context-aware Dynamic Speculative Sampling for Large-Vocabulary Language Models
por: Zhang, Jinbin, et al.
Publicado: (2025)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
por: Yang, Rubing, et al.
Publicado: (2025)

Sequence-to-Sequence Language Models for Character and Emotion Detection in Dream Narratives
por: Cortal, Gustave
Publicado: (2024)

Leveraging Large Language Models for Active Merchant Non-player Characters
por: Kim, Byungjun, et al.
Publicado: (2024)

The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling
por: Zhang, Ruochen, et al.
Publicado: (2024)

Building Models of Neurological Language
por: Watkins, Henry
Publicado: (2025)

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
por: Zhao, Weilin, et al.
Publicado: (2025)

Towards Measuring the Representation of Subjective Global Opinions in Language Models
por: Durmus, Esin, et al.
Publicado: (2023)

Collective Constitutional AI: Aligning a Language Model with Public Input
por: Huang, Saffron, et al.
Publicado: (2024)

Persona Vectors: Monitoring and Controlling Character Traits in Language Models
por: Chen, Runjin, et al.
Publicado: (2025)

Differences in Text Generated by Diffusion and Autoregressive Language Models
por: Zhang, Zeyang, et al.
Publicado: (2026)

Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models
por: Liu, Xin, et al.
Publicado: (2025)

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models
por: Ensign, Danielle, et al.
Publicado: (2025)

R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models
por: Tu, Shangqing, et al.
Publicado: (2024)

Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks
por: Zhou, Yue, et al.
Publicado: (2024)

Revisiting Character-level Adversarial Attacks for Language Models
por: Rocamora, Elias Abad, et al.
Publicado: (2024)

Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
por: Slocum, Stewart, et al.
Publicado: (2025)

Hierarchical Orthogonal Residual Spread for Precise Massive Editing in Large Language Models
por: Gu, Xiaojie, et al.
Publicado: (2026)

Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
por: Xu, Xiaoyue, et al.
Publicado: (2024)

Towards Data Contamination Detection for Modern Large Language Models: Limitations, Inconsistencies, and Oracle Challenges
por: Samuel, Vinay, et al.
Publicado: (2024)

Revealing the Inherent Instructability of Pre-Trained Language Models
por: An, Seokhyun, et al.
Publicado: (2024)

InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling
por: Diao, Xiaolei, et al.
Publicado: (2025)

Training-Free Test-Time Contrastive Learning for Large Language Models
por: Zheng, Kaiwen, et al.
Publicado: (2026)

Inverse Scaling in Test-Time Compute
por: Gema, Aryo Pradipta, et al.
Publicado: (2025)

MMLU-SR: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models
por: Wang, Wentian, et al.
Publicado: (2024)

Language Model Distillation: A Temporal Difference Imitation Learning Perspective
por: Yu, Zishun, et al.
Publicado: (2025)

Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector
por: Zhang, Andi, et al.
Publicado: (2024)

Revealing the Intrinsic Ethical Vulnerability of Aligned Large Language Models
por: Lian, Jiawei, et al.
Publicado: (2025)

When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models
por: Wu, Huyu, et al.
Publicado: (2025)

Component-Level Lesioning of Language Models Reveals Clinically Aligned Aphasia Phenotypes
por: Wang, Yifan, et al.
Publicado: (2026)

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
por: Wang, Cheng, et al.
Publicado: (2025)

Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
por: Xie, Jian, et al.
Publicado: (2023)