33 citations · 127 across the 31 of their papers we have counts for
9 papers · 1 filter
What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs
Nhi Nguyen, Shauli Ravfogel, Rajesh Ranganath
Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify mod…
The Truthfulness Spectrum Hypothesis
Zhuofan Josh Ying, Shauli Ravfogel, Nikolaus Kriegeskorte +1
Large language models (LLMs) have been reported to linearly encode truthfulness, yet recent work questions this finding's generality. We reconcile these views with the truthfulness…
Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks
Itamar Trainin, Shauli Ravfogel, Omri Abend +1
While Autoregressive (AR) Transformer-based Generative Language Models are frequently employed for lookahead tasks, recent research suggests a potential discrepancy in their abilit…
Representation Surgery: Theory and Practice of Affine Steering
Shashwat Singh, Shauli Ravfogel, Jonathan Herzig +3
Language models often exhibit undesirable behavior, e.g., generating toxic or gender-biased text. In the case of neural language models, an encoding of the undesirable behavior is…
LEACE: Perfect linear concept erasure in closed form
Nora Belrose, David Schneider-Joseph, Shauli Ravfogel +3
Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. rem…
Log-linear Guardedness and its Implications
Shauli Ravfogel, Yoav Goldberg, Ryan Cotterell
Methods for erasing human-interpretable concepts from neural representations that assume linearity have been found to be tractable and useful. However, the impact of this removal o…
Kernelized Concept Erasure
Shauli Ravfogel, Francisco Vargas, Yoav Goldberg +1
The representation space of neural models for textual data emerges in an unsupervised manner during training. Understanding how those representations encode human-interpretable con…
Linear Adversarial Concept Erasure
Shauli Ravfogel, Michael Twiton, Yoav Goldberg +1
Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision. As these representations are increasingly being used in rea…
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
Elad Ben-Zaken, Shauli Ravfogel, Yoav Goldberg
We introduce BitFit, a sparse-finetuning method where only the bias-terms of the model (or a subset of them) are being modified. We show that with small-to-medium training data, ap…