Mor Geva
- Papers
- 33
Cite
Notes
Only stored in your browser.
Authored papers
33Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
arXiv 2026
Rethinking Selective Knowledge Distillation
arXiv 2026
From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
arXiv 2026
Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models
arXiv 2026
Precise In-Parameter Concept Erasure in Large Language Models
arXiv 2025
Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
arXiv 2025
Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization
arXiv 2025
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
arXiv 2025
Enhancing Automated Interpretability with Output-Centric Feature Descriptions
arXiv 2025
Universal Jailbreak Suffixes Are Strong Attention Hijackers
arXiv 2025
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
arXiv 2025
Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?
arXiv 2024
RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations
arXiv 2024
Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries
arXiv 2024
Inferring Functionality of Attention Heads from their Parameters
arXiv 2024
From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP
arXiv 2024
The Hidden Space of Transformer Language Adapters
arXiv 2024
Towards Interpreting Visual Information Processing in Vision-Language Models
arXiv 2024
Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces
arXiv 2024
From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty
arXiv 2024
Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language Models
arXiv 2024
In-Context Learning Creates Task Vectors
arXiv 2023
Evaluating the Ripple Effects of Knowledge Editing in Language Models
arXiv 2023
Jump to Conclusions: Short-Cutting Transformers With Linear Transformations
arXiv 2023
The Hidden Language of Diffusion Models
arXiv 2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
arXiv 2022
SCROLLS: Standardized CompaRison Over Long Language Sequences
arXiv 2022
Analyzing Transformers in Embedding Space
arXiv 2022
Inferring Implicit Relations in Complex Questions with Language Models
arXiv 2022
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
arXiv 2021
Injecting Numerical Reasoning Skills into Language Models
injecting-numerical-reasoning-skills-into-1
Transformer Feed-Forward Layers Are Key-Value Memories
EMNLP 2021 11
Affiliations
Frequent co-authors
10from 33 papers