Imagen de Portada

Robust Infidelity: When Faithfulness Measures on Masked Language Models Are Misleading

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Crothers, Evan, Viktor, Herna, Japkowicz, Nathalie
Formato:	Preprint
Publicado:	2023
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Don't be Tricked by Iterative Masking
por: Evan Crothers, et al.
Publicado: (2026)

Faithfulness Measurable Masked Language Models
por: Madsen, Andreas, et al.
Publicado: (2023)

Monitoring the evolution of antisemitic discourse on extremist social media using BERT
por: Mustafa, Raza Ul, et al.
Publicado: (2024)

When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards
por: Wang, Li, et al.
Publicado: (2026)

Learning Shortcuts: On the Misleading Promise of NLU in Language Models
por: Bihani, Geetanjali, et al.
Publicado: (2024)

Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
por: Matton, Katie, et al.
Publicado: (2025)

Mapping Faithful Reasoning in Language Models
por: Li, Jiazheng, et al.
Publicado: (2025)

Exploring the Potential of the Large Language Models (LLMs) in Identifying Misleading News Headlines
por: Rony, Md Main Uddin, et al.
Publicado: (2024)

E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detection
por: Mousavi, Ahmad, et al.
Publicado: (2025)

MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs
por: Liu, Gabrielle Kaili-May, et al.
Publicado: (2025)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
por: Hanna, Michael, et al.
Publicado: (2024)

FaithLM: Towards Faithful Explanations for Large Language Models
por: Chuang, Yu-Neng, et al.
Publicado: (2024)

Faithful and Robust Local Interpretability for Textual Predictions
por: Lopardo, Gianluigi, et al.
Publicado: (2023)

Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead
por: Kang, Feiyang, et al.
Publicado: (2025)

RePro: Training Language Models to Faithfully Recycle the Web for Pretraining
por: Yu, Zichun, et al.
Publicado: (2025)

Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical Medicine
por: Liu, Fenglin, et al.
Publicado: (2022)

Representation Deficiency in Masked Language Modeling
por: Meng, Yu, et al.
Publicado: (2023)

Transformer Circuit Faithfulness Metrics are not Robust
por: Miller, Joseph, et al.
Publicado: (2024)

Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering
por: Schimanski, Tobias, et al.
Publicado: (2024)

Contextual Text Denoising with Masked Language Models
por: Sun, Yifu, et al.
Publicado: (2019)

Scaling Beyond Masked Diffusion Language Models
por: Sahoo, Subham Sekhar, et al.
Publicado: (2026)

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
por: Ming, Yifei, et al.
Publicado: (2024)

New Faithfulness-Centric Interpretability Paradigms for Natural Language Processing
por: Madsen, Andreas
Publicado: (2024)

Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification
por: AlMarri, Saeed, et al.
Publicado: (2025)

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
por: Huang, Yanwen, et al.
Publicado: (2025)

Using LLMs to discover emerging coded antisemitic hate-speech in extremist social media
por: Kikkisetti, Dhanush, et al.
Publicado: (2024)

Cycles of Thought: Measuring LLM Confidence through Stable Explanations
por: Becker, Evan, et al.
Publicado: (2024)

Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity
por: Meek, Austin, et al.
Publicado: (2025)

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
por: Jia, Jinghan, et al.
Publicado: (2026)

SoftHateBench: Evaluating Moderation Models Against Reasoning-Driven, Policy-Compliant Hostility
por: Su, Xuanyu, et al.
Publicado: (2026)

Towards Probabilistically-Sound Beam Search with Masked Language Models
por: Brooks, Creston, et al.
Publicado: (2024)

Diffusion-State Policy Optimization for Masked Diffusion Language Models
por: Oba, Daisuke, et al.
Publicado: (2026)

DOS: Dependency-Oriented Sampler for Masked Diffusion Language Models
por: Zhou, Xueyu, et al.
Publicado: (2026)

Reconsidering Positional Supervision in Masked Diffusion Language Model Training
por: Ye, Mengyu, et al.
Publicado: (2026)

Self-Taught Self-Correction for Small Language Models
por: Moskvoretskii, Viktor, et al.
Publicado: (2025)

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
por: Wang, Tianchun, et al.
Publicado: (2024)

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
por: Anand, Nikhil, et al.
Publicado: (2026)

ExLM: Rethinking the Impact of [MASK] Tokens in Masked Language Models
por: Zheng, Kangjie, et al.
Publicado: (2025)

Masked Mixers for Language Generation and Retrieval
por: Badger, Benjamin L.
Publicado: (2024)

Soft-Masked Diffusion Language Models
por: Hersche, Michael, et al.
Publicado: (2025)