Guardado en:
| Autores principales: | Ravfogel, Shauli, Yehudai, Gilad, Linzen, Tal, Bruna, Joan, Bietti, Alberto |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2510.15804 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
Geometric Factual Recall in Transformers
por: Ravfogel, Shauli, et al.
Publicado: (2026)
por: Ravfogel, Shauli, et al.
Publicado: (2026)
RELIC: Evaluating Complex Reasoning via the Recognition of Languages In-Context
por: Petty, Jackson, et al.
Publicado: (2025)
por: Petty, Jackson, et al.
Publicado: (2025)
Can LLMs Introspect? A Reality Check
por: Singh, Shashwat, et al.
Publicado: (2026)
por: Singh, Shashwat, et al.
Publicado: (2026)
Compositional Reasoning with Transformers, RNNs, and Chain of Thought
por: Yehudai, Gilad, et al.
Publicado: (2025)
por: Yehudai, Gilad, et al.
Publicado: (2025)
Linear Adversarial Concept Erasure
por: Ravfogel, Shauli, et al.
Publicado: (2022)
por: Ravfogel, Shauli, et al.
Publicado: (2022)
Do Language Models' Words Refer?
por: Mandelkern, Matthew, et al.
Publicado: (2023)
por: Mandelkern, Matthew, et al.
Publicado: (2023)
Gumbel Counterfactual Generation From Language Models
por: Ravfogel, Shauli, et al.
Publicado: (2024)
por: Ravfogel, Shauli, et al.
Publicado: (2024)
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
por: Ben-Zaken, Elad, et al.
Publicado: (2021)
por: Ben-Zaken, Elad, et al.
Publicado: (2021)
Log-linear Guardedness and its Implications
por: Ravfogel, Shauli, et al.
Publicado: (2022)
por: Ravfogel, Shauli, et al.
Publicado: (2022)
Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers
por: Chen, Lei, et al.
Publicado: (2024)
por: Chen, Lei, et al.
Publicado: (2024)
From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
por: Shafran, Or, et al.
Publicado: (2026)
por: Shafran, Or, et al.
Publicado: (2026)
The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure
por: Fan, Yu, et al.
Publicado: (2025)
por: Fan, Yu, et al.
Publicado: (2025)
Entailment Semantics Can Be Extracted from an Ideal Language Model
por: Merrill, William, et al.
Publicado: (2022)
por: Merrill, William, et al.
Publicado: (2022)
A Practical Method for Generating String Counterfactuals
por: Avitan, Matan, et al.
Publicado: (2024)
por: Avitan, Matan, et al.
Publicado: (2024)
State over Tokens: Characterizing the Role of Reasoning Tokens
por: Levy, Mosh, et al.
Publicado: (2025)
por: Levy, Mosh, et al.
Publicado: (2025)
Kernelized Concept Erasure
por: Ravfogel, Shauli, et al.
Publicado: (2022)
por: Ravfogel, Shauli, et al.
Publicado: (2022)
The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments
por: Schäfer, Anton, et al.
Publicado: (2024)
por: Schäfer, Anton, et al.
Publicado: (2024)
SPAWNing Structural Priming Predictions from a Cognitively Motivated Parser
por: Prasad, Grusha, et al.
Publicado: (2024)
por: Prasad, Grusha, et al.
Publicado: (2024)
Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval
por: Chen, Hung-Ting, et al.
Publicado: (2025)
por: Chen, Hung-Ting, et al.
Publicado: (2025)
Diversity Over Quantity: A Lesson From Few Shot Relation Classification
por: Cohen, Amir DN, et al.
Publicado: (2024)
por: Cohen, Amir DN, et al.
Publicado: (2024)
How Does Code Pretraining Affect Language Model Task Performance?
por: Petty, Jackson, et al.
Publicado: (2024)
por: Petty, Jackson, et al.
Publicado: (2024)
Intrinsic Test of Unlearning Using Parametric Knowledge Traces
por: Hong, Yihuai, et al.
Publicado: (2024)
por: Hong, Yihuai, et al.
Publicado: (2024)
IQ Test for LLMs: An Evaluation Framework for Uncovering Core Skills in LLMs
por: Maimon, Aviya, et al.
Publicado: (2025)
por: Maimon, Aviya, et al.
Publicado: (2025)
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
por: Rassin, Royi, et al.
Publicado: (2023)
por: Rassin, Royi, et al.
Publicado: (2023)
Language Models Struggle to Use Representations Learned In-Context
por: Lepori, Michael A., et al.
Publicado: (2026)
por: Lepori, Michael A., et al.
Publicado: (2026)
Deconstructing sentence disambiguation by joint latent modeling of reading paradigms: LLM surprisal is not enough
por: Paape, Dario, et al.
Publicado: (2026)
por: Paape, Dario, et al.
Publicado: (2026)
Manipulating language models' training data to study syntactic constraint learning: the case of English passivization
por: Leong, Cara Su-Yi, et al.
Publicado: (2024)
por: Leong, Cara Su-Yi, et al.
Publicado: (2024)
Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis
por: Timkey, William, et al.
Publicado: (2026)
por: Timkey, William, et al.
Publicado: (2026)
Representation Surgery: Theory and Practice of Affine Steering
por: Singh, Shashwat, et al.
Publicado: (2024)
por: Singh, Shashwat, et al.
Publicado: (2024)
Description-Based Text Similarity
por: Ravfogel, Shauli, et al.
Publicado: (2023)
por: Ravfogel, Shauli, et al.
Publicado: (2023)
Evaluating In-Context Translation with Synchronous Context-Free Grammar Transduction
por: Petty, Jackson, et al.
Publicado: (2026)
por: Petty, Jackson, et al.
Publicado: (2026)
LEACE: Perfect linear concept erasure in closed form
por: Belrose, Nora, et al.
Publicado: (2023)
por: Belrose, Nora, et al.
Publicado: (2023)
The Impact of Depth on Compositional Generalization in Transformer Language Models
por: Petty, Jackson, et al.
Publicado: (2023)
por: Petty, Jackson, et al.
Publicado: (2023)
The Truthfulness Spectrum Hypothesis
por: Ying, Zhuofan Josh, et al.
Publicado: (2026)
por: Ying, Zhuofan Josh, et al.
Publicado: (2026)
On the Benefits of Rank in Attention Layers
por: Amsel, Noah, et al.
Publicado: (2024)
por: Amsel, Noah, et al.
Publicado: (2024)
Multilingual Prompting for Improving LLM Generation Diversity
por: Wang, Qihan, et al.
Publicado: (2025)
por: Wang, Qihan, et al.
Publicado: (2025)
What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Length
por: Tjuatja, Lindia, et al.
Publicado: (2024)
por: Tjuatja, Lindia, et al.
Publicado: (2024)
In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax
por: Mueller, Aaron, et al.
Publicado: (2023)
por: Mueller, Aaron, et al.
Publicado: (2023)
Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models
por: Qiu, Linlu, et al.
Publicado: (2025)
por: Qiu, Linlu, et al.
Publicado: (2025)
Preserving Task-Relevant Information Under Linear Concept Removal
por: Holstege, Floris, et al.
Publicado: (2025)
por: Holstege, Floris, et al.
Publicado: (2025)
Ejemplares similares
-
Geometric Factual Recall in Transformers
por: Ravfogel, Shauli, et al.
Publicado: (2026) -
RELIC: Evaluating Complex Reasoning via the Recognition of Languages In-Context
por: Petty, Jackson, et al.
Publicado: (2025) -
Can LLMs Introspect? A Reality Check
por: Singh, Shashwat, et al.
Publicado: (2026) -
Compositional Reasoning with Transformers, RNNs, and Chain of Thought
por: Yehudai, Gilad, et al.
Publicado: (2025) -
Linear Adversarial Concept Erasure
por: Ravfogel, Shauli, et al.
Publicado: (2022)