Copertina

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wong, Sing Hieng, Sajjad, Hassan, Siddique, A. B.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
di: Marks, Samuel, et al.
Pubblicazione: (2024)

Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
di: Lamb, Tom A., et al.
Pubblicazione: (2024)

Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution
di: Haider, Muhammad Umair, et al.
Pubblicazione: (2025)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
di: Chalnev, Sviatoslav, et al.
Pubblicazione: (2024)

Cross-Layer Discrete Concept Discovery for Interpreting Language Models
di: Garg, Ankur, et al.
Pubblicazione: (2025)

Interpretable Steering of Large Language Models with Feature Guided Activation Additions
di: Soo, Samuel, et al.
Pubblicazione: (2025)

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
di: He, Zirui, et al.
Pubblicazione: (2025)

Compositional Steering of Large Language Models with Steering Tokens
di: Radevski, Gorjan, et al.
Pubblicazione: (2026)

Interpreting the Effects of Quantization on LLMs
di: Singh, Manpreet, et al.
Pubblicazione: (2025)

Quantifying the Capabilities of LLMs across Scale and Precision
di: Badshah, Sher, et al.
Pubblicazione: (2024)

Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
di: Siddique, Zara, et al.
Pubblicazione: (2025)

Discovering Forbidden Topics in Language Models
di: Rager, Can, et al.
Pubblicazione: (2025)

Word Embeddings Are Steers for Language Models
di: Han, Chi, et al.
Pubblicazione: (2023)

Endogenous Resistance to Activation Steering in Language Models
di: McKenzie, Alex, et al.
Pubblicazione: (2026)

Can Language Models Discover Scaling Laws?
di: Lin, Haowei, et al.
Pubblicazione: (2025)

LangTopo: Aligning Language Descriptions of Graphs with Tokenized Topological Modeling
di: Guan, Zhong, et al.
Pubblicazione: (2024)

LangProBe: a Language Programs Benchmark
di: Tan, Shangyin, et al.
Pubblicazione: (2025)

Discovering Latent Knowledge in Language Models Without Supervision
di: Burns, Collin, et al.
Pubblicazione: (2022)

Discovering Knowledge-Critical Subnetworks in Pretrained Language Models
di: Bayazit, Deniz, et al.
Pubblicazione: (2023)

COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
di: Sharma, Kartik, et al.
Pubblicazione: (2026)

Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
di: Lan, Michael, et al.
Pubblicazione: (2024)

Steering Large Language Models for Machine Translation Personalization
di: Scalena, Daniel, et al.
Pubblicazione: (2025)

Task-Specific Sparse Feature Masks for Molecular Toxicity Prediction with Chemical Language Models
di: Lee, Kwun Sy, et al.
Pubblicazione: (2025)

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
di: Weng, Zixuan, et al.
Pubblicazione: (2026)

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
di: Yu, Zhuohao, et al.
Pubblicazione: (2025)

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
di: Wang, Zhilin, et al.
Pubblicazione: (2025)

Improving Instruction-Following in Language Models through Activation Steering
di: Stolfo, Alessandro, et al.
Pubblicazione: (2024)

Multi-Attribute Steering of Language Models via Targeted Intervention
di: Nguyen, Duy, et al.
Pubblicazione: (2025)

The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
di: Xu, Yi, et al.
Pubblicazione: (2026)

Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder
di: Yang, Xianjun, et al.
Pubblicazione: (2025)

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines
di: Jørgensen, Mikkel Godsk, et al.
Pubblicazione: (2026)

SAEs Are Good for Steering -- If You Select the Right Features
di: Arad, Dana, et al.
Pubblicazione: (2025)

Multi-property Steering of Large Language Models with Dynamic Activation Composition
di: Scalena, Daniel, et al.
Pubblicazione: (2024)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
di: Oozeer, Narmeen, et al.
Pubblicazione: (2025)

ILRR: Inference-Time Steering Method for Masked Diffusion Language Models
di: Avrahami, Eden, et al.
Pubblicazione: (2026)

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

UniMaia: Steering Chess Policies with Language for Human-like Play
di: Siu, Sherman, et al.
Pubblicazione: (2026)

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning
di: Jin, Jikai, et al.
Pubblicazione: (2025)

Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models
di: Zhou, Hanhan, et al.
Pubblicazione: (2026)

That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation
di: Bae, Jaesung, et al.
Pubblicazione: (2025)