Imagen de Portada

InversionView: A General-Purpose Method for Reading Information from Neural Activations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Xinting, Panwar, Madhur, Goyal, Navin, Hahn, Michael
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

In-Context Learning through the Bayesian Prism
por: Panwar, Madhur, et al.
Publicado: (2023)

Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
por: Huang, Xinting, et al.
Publicado: (2025)

Discovering Interpretable Algorithms by Decompiling Transformers to RASP
por: Huang, Xinting, et al.
Publicado: (2026)

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
por: Karvonen, Adam, et al.
Publicado: (2025)

Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers
por: Ahuja, Kabir, et al.
Publicado: (2024)

DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization
por: Huang, Chengyu, et al.
Publicado: (2025)

Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains
por: Shen, Junhong, et al.
Publicado: (2024)

Advancing General-Purpose Reasoning Models with Modular Gradient Surgery
por: Cai, Min, et al.
Publicado: (2026)

Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ?
por: Chiaranaipanich, Jirat, et al.
Publicado: (2024)

LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training
por: Wang, Yiming, et al.
Publicado: (2025)

Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
por: Wang, Boxin, et al.
Publicado: (2025)

Agentic AI framework for End-to-End Medical Data Inference
por: Shimgekar, Soorya Ram, et al.
Publicado: (2025)

A comprehensive study of on-device NLP applications -- VQA, automated Form filling, Smart Replies for Linguistic Codeswitching
por: Goyal, Naman
Publicado: (2024)

Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability
por: Chung, Tsz Ting, et al.
Publicado: (2024)

Extracting Unlearned Information from LLMs with Activation Steering
por: Seyitoğlu, Atakan, et al.
Publicado: (2024)

Empowering Small-Scale Knowledge Graphs: A Strategy of Leveraging General-Purpose Knowledge Graphs for Enriched Embeddings
por: Sawczyn, Albert, et al.
Publicado: (2024)

Addressing LLM Diversity by Infusing Random Concepts
por: Agrawal, Pulin, et al.
Publicado: (2026)

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
por: Zhang, Fred, et al.
Publicado: (2023)

Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification
por: Khatuya, Subhendu, et al.
Publicado: (2025)

LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations
por: Lugoloobi, William, et al.
Publicado: (2026)

Memorization vs. Reasoning: Updating LLMs with New Knowledge
por: Li, Aochong Oliver, et al.
Publicado: (2025)

Steering Safely or Off a Cliff? Rethinking Specificity and Robustness in Inference-Time Interventions
por: Goyal, Navita, et al.
Publicado: (2026)

Learning a Generative Meta-Model of LLM Activations
por: Luo, Grace, et al.
Publicado: (2026)

DigiData: Training and Evaluating General-Purpose Mobile Control Agents
por: Sun, Yuxuan, et al.
Publicado: (2025)

Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis
por: Voigt, Henrik, et al.
Publicado: (2026)

AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?
por: Press, Ori, et al.
Publicado: (2025)

LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Model
por: Salles, Marcel Mateos, et al.
Publicado: (2025)

Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL
por: Hoffmann, Jessica, et al.
Publicado: (2025)

MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy
por: Yoshida, Davis, et al.
Publicado: (2023)

Debate Helps Weak Judges Reward Stronger Models
por: Elasky, Ethan, et al.
Publicado: (2026)

SERPENT-VLM : Self-Refining Radiology Report Generation Using Vision Language Models
por: Kapadnis, Manav Nitin, et al.
Publicado: (2024)

Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B
por: Bakalova, Aleksandra, et al.
Publicado: (2025)

Was it Slander? Towards Exact Inversion of Generative Language Models
por: Skapars, Adrians, et al.
Publicado: (2024)

You Don't Need Prompt Engineering Anymore: The Prompting Inversion
por: Khan, Imran
Publicado: (2025)

Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion
por: Tan, Zhen, et al.
Publicado: (2026)

HyperSteer: Activation Steering at Scale with Hypernetworks
por: Sun, Jiuding, et al.
Publicado: (2025)

Mode-Conditioning Unlocks Superior Test-Time Scaling
por: Wu, Chen Henry, et al.
Publicado: (2025)

Can Models Learn Skill Composition from Examples?
por: Zhao, Haoyu, et al.
Publicado: (2024)

View From Above: A Framework for Evaluating Distribution Shifts in Model Behavior
por: Chopra, Tanush, et al.
Publicado: (2024)

Understanding Generalization in Role-Playing Models via Information Theory
por: Li, Yongqi, et al.
Publicado: (2025)