Imagen de Portada

Jinx: Unlimited LLMs for Probing Alignment Failures

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Jiahao, Dong, Liwei
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

Medal Matters: Probing LLMs' Failure Cases Through Olympic Rankings
por: Choi, Juhwan, et al.
Publicado: (2024)

Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs
por: Liu, Jiahao, et al.
Publicado: (2025)

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
por: Ma, Xuezhe, et al.
Publicado: (2024)

Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
por: Qin, Zhen, et al.
Publicado: (2024)

Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs
por: Chen, Angelica, et al.
Publicado: (2023)

Probing Multimodal Large Language Models for Global and Local Semantic Representations
por: Tao, Mingxu, et al.
Publicado: (2024)

What are They Thinking? Delineation, Probing and Tracking of Concepts in LLMs
por: Abdelwahab, Mohamed, et al.
Publicado: (2026)

Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
por: Ren, Liliang, et al.
Publicado: (2024)

RAG-E: Quantifying Retriever-Generator Alignment and Failure Modes
por: Randl, Korbinian, et al.
Publicado: (2026)

LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning
por: Zhao, Jiahao
Publicado: (2025)

REAL: Response Embedding-based Alignment for LLMs
por: Zhang, Honggen, et al.
Publicado: (2024)

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
por: Liang, Juhao, et al.
Publicado: (2024)

Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration
por: Li, Qintong, et al.
Publicado: (2024)

PACIFIC: Can LLMs Discern the Traits Influencing Your Preferences? Evaluating Personality-Driven Preference Alignment in LLMs
por: Zhao, Tianyu, et al.
Publicado: (2026)

Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
por: Patel, Nyal, et al.
Publicado: (2025)

Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities
por: Saporta, Adriel, et al.
Publicado: (2024)

Teaching LLMs to Refine with Tools
por: Yu, Dian, et al.
Publicado: (2024)

ProbeLLM: Automating Principled Diagnosis of LLM Failures
por: Huang, Yue, et al.
Publicado: (2026)

Evaluating Alignment of Behavioral Dispositions in LLMs
por: Taubenfeld, Amir, et al.
Publicado: (2026)

Concept Space Alignment in Multilingual LLMs
por: Peng, Qiwei, et al.
Publicado: (2024)

Cultural Palette: Pluralising Culture Alignment via Multi-agent Palette
por: Yuan, Jiahao, et al.
Publicado: (2024)

PluralLLM: Pluralistic Alignment in LLMs via Federated Learning
por: Srewa, Mahmoud, et al.
Publicado: (2025)

Survey-to-Behavior: Downstream Alignment of Human Values in LLMs via Survey Questions
por: Nie, Shangrui, et al.
Publicado: (2025)

Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning
por: Choenni, Rochelle, et al.
Publicado: (2024)

Improving the Distributional Alignment of LLMs using Supervision
por: Kambhatla, Gauri, et al.
Publicado: (2025)

HAL: Inducing Human-likeness in LLMs with Alignment
por: Hasan, Masum, et al.
Publicado: (2026)

Failure Modes of LLMs for Causal Reasoning on Narratives
por: Yamin, Khurram, et al.
Publicado: (2024)

Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment
por: Deng, Jingcheng, et al.
Publicado: (2025)

Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
por: Yeom, Jewon, et al.
Publicado: (2026)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
por: Li, Li, et al.
Publicado: (2025)

LLM Probe: Evaluating LLMs for Low-Resource Languages
por: Teklehaymanot, Hailay Kidu, et al.
Publicado: (2026)

Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing
por: Zhao, Raoyuan, et al.
Publicado: (2025)

How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction
por: He, Yingjie, et al.
Publicado: (2026)

Can LLMs Express Personality Across Cultures? Introducing CulturalPersonas for Evaluating Trait Alignment
por: Dey, Priyanka, et al.
Publicado: (2025)

Panacea: Pareto Alignment via Preference Adaptation for LLMs
por: Zhong, Yifan, et al.
Publicado: (2024)

Xwin-LM: Strong and Scalable Alignment Practice for LLMs
por: Ni, Bolin, et al.
Publicado: (2024)

Impact of Decoding Methods on Human Alignment of Conversational LLMs
por: Furniturewala, Shaz, et al.
Publicado: (2024)

A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs
por: Srewa, Mahmoud, et al.
Publicado: (2025)

Probing the Limits of Stylistic Alignment in Vision-Language Models
por: Farajidizaji, Asma, et al.
Publicado: (2025)

Alignment is Localized: A Causal Probe into Preference Layers
por: Chaudhury, Archie
Publicado: (2025)