FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
by: Cho, Seonglae, et al.
Published: (2025)
by: Cho, Seonglae, et al.
Published: (2025)
Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
by: Cho, Seonglae, et al.
Published: (2026)
by: Cho, Seonglae, et al.
Published: (2026)
Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
by: Xiong, Guangzhi, et al.
Published: (2025)
by: Xiong, Guangzhi, et al.
Published: (2025)
TimeSAE: Sparse Decoding for Faithful Explanations of Black-Box Time Series Models
by: Oublal, Khalid, et al.
Published: (2026)
by: Oublal, Khalid, et al.
Published: (2026)
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
by: Korznikov, Anton, et al.
Published: (2025)
by: Korznikov, Anton, et al.
Published: (2025)
Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders
by: Cao, Tue M., et al.
Published: (2026)
by: Cao, Tue M., et al.
Published: (2026)
FaithCAMERA: Construction of a Faithful Dataset for Ad Text Generation
by: Kato, Akihiko, et al.
Published: (2024)
by: Kato, Akihiko, et al.
Published: (2024)
Sparse and Faithful Explanations Without Sparse Models
by: Sun, Yiyang, et al.
Published: (2024)
by: Sun, Yiyang, et al.
Published: (2024)
PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
by: Koromilas, Panagiotis, et al.
Published: (2026)
by: Koromilas, Panagiotis, et al.
Published: (2026)
FaithLM: Towards Faithful Explanations for Large Language Models
by: Chuang, Yu-Neng, et al.
Published: (2024)
by: Chuang, Yu-Neng, et al.
Published: (2024)
AlignSAE: Concept-Aligned Sparse Autoencoders
by: Yang, Minglai, et al.
Published: (2025)
by: Yang, Minglai, et al.
Published: (2025)
Faith in Law, Law in Faith
Published: (2024)
Published: (2024)
SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models
by: Zhang, Mingxu, et al.
Published: (2026)
by: Zhang, Mingxu, et al.
Published: (2026)
FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge
by: Yang, Nakyeong, et al.
Published: (2025)
by: Yang, Nakyeong, et al.
Published: (2025)
RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation
by: Tan, Xianfeng, et al.
Published: (2024)
by: Tan, Xianfeng, et al.
Published: (2024)
SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection
by: Zhang, Huopu, et al.
Published: (2025)
by: Zhang, Huopu, et al.
Published: (2025)
FaithRL: Learning to Reason Faithfully through Step-Level Faithfulness Maximization
by: Gui, Runquan, et al.
Published: (2026)
by: Gui, Runquan, et al.
Published: (2026)
Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
by: Ju, Li, et al.
Published: (2026)
by: Ju, Li, et al.
Published: (2026)
LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer
by: Panda, Raina, et al.
Published: (2025)
by: Panda, Raina, et al.
Published: (2025)
MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders
by: Renzulli, Riccardo, et al.
Published: (2025)
by: Renzulli, Riccardo, et al.
Published: (2025)
FaithLens: Detecting and Explaining Faithfulness Hallucination
by: Si, Shuzheng, et al.
Published: (2025)
by: Si, Shuzheng, et al.
Published: (2025)
Faith seeking understanding
by: Vorster, J.M., et al.
Published: (2022)
by: Vorster, J.M., et al.
Published: (2022)
Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)
by: Brzozowski, Michał, et al.
Published: (2026)
by: Brzozowski, Michał, et al.
Published: (2026)
Faithful action of braid group on bosonic extensions
by: Kashiwara, Masaki, et al.
Published: (2025)
by: Kashiwara, Masaki, et al.
Published: (2025)
LegalFaith: A Faithfulness Benchmark for Legal QA
by: Singh, Rajshree
Published: (2026)
by: Singh, Rajshree
Published: (2026)
Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning
by: Afolabi, Halimat, et al.
Published: (2026)
by: Afolabi, Halimat, et al.
Published: (2026)
ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions
by: Poduval, Prathyush, et al.
Published: (2026)
by: Poduval, Prathyush, et al.
Published: (2026)
Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders
by: Nakka, Krishna Kanth
Published: (2025)
by: Nakka, Krishna Kanth
Published: (2025)
SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders
by: Stępień, Jakub, et al.
Published: (2026)
by: Stępień, Jakub, et al.
Published: (2026)
Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
by: Liu, Fanzhen, et al.
Published: (2025)
by: Liu, Fanzhen, et al.
Published: (2025)
Faith Honoring
by: Lindsey, Jill L., et al.
Published: (2024)
by: Lindsey, Jill L., et al.
Published: (2024)
Faithful perversities
by: Cipriani, Alessio, et al.
Published: (2026)
by: Cipriani, Alessio, et al.
Published: (2026)