6 citations · 18 across the 14 of their papers we have counts for
14 papers
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
Atoosa Chegini, Soheil Feizi
Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to i…
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
Hamid Kazemi, Atoosa Chegini, Maria Safi
Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expressed, and concept neurons tha…
Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection
Atoosa Chegini, Hamid Kazemi, Garrett Souza +5
Reasoning has become a central paradigm for large language models (LLMs), consistently boosting accuracy across diverse benchmarks. Yet its suitability for precision-sensitive task…
RePanda: Pandas-powered Tabular Verification and Reasoning
Atoosa Malemir Chegini, Keivan Rezaei, Hamid Eghbalzadeh +1
Fact-checking tabular data is essential for ensuring the accuracy of structured information. However, existing methods often rely on black-box models with opaque reasoning. We intr…
SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
Atoosa Chegini, Hamid Kazemi, Iman Mirzadeh +5
In Large Language Model (LLM) development, Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning models with human values and preferences. RLHF traditionally re…
Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models
Mazda Moayeri, Samyadeep Basu, Sriram Balasubramanian +4
Recent text-to-image generative models such as Stable Diffusion are extremely adept at mimicking and generating copyrighted content, raising concerns amongst artists that their uni…
What do we learn from inverting CLIP models?
Hamid Kazemi, Atoosa Chegini, Jonas Geiping +2
We employ an inversion-based approach to examine CLIP models. Our examination reveals that inverting CLIP models results in the generation of images that exhibit semantic alignment…
Fast Adversarial Attacks on Language Models In One GPU Minute
Vinu Sankar Sadasivan, Shoumik Saha, Gaurang Sriramanan +3
In this paper, we introduce a novel class of fast, beam search-based adversarial attack (BEAST) for Language Models (LMs). BEAST employs interpretable parameters, enabling attacker…
Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation
Atoosa Chegini, Soheil Feizi
Deep learning models can encounter unexpected failures, especially when dealing with challenging sub-populations. One common reason for these failures is the occurrence of objects…
EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods
Samyadeep Basu, Mehrdad Saberi, Shweta Bhardwaj +5
A plethora of text-guided image editing methods have recently been developed by leveraging the impressive capabilities of large-scale diffusion-based generative models such as Imag…
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei +4
In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materia…
Run-Off Election: Improved Provable Defense against Data Poisoning Attacks
Keivan Rezaei, Kiarash Banihashem, Atoosa Chegini +1
In data poisoning attacks, an adversary tries to change a model's prediction by adding, modifying, or removing samples in the training data. Recently, ensemble-based approaches for…
Data-Centric Debugging: mitigating model failures via targeted data collection
Sahil Singla, Atoosa Malemir Chegini, Mazda Moayeri +1
Deep neural networks can be unreliable in the real world when the training set does not adequately cover all the settings where they are deployed. Focusing on image classification,…
InForecaster: Forecasting Influenza Hemagglutinin Mutations Through the Lens of Anomaly Detection
Ali Garjani, Atoosa Malemir Chegini, Mohammadreza Salehi +6
The influenza virus hemagglutinin is an important part of the virus attachment to the host cells. The hemagglutinin proteins are one of the genetic regions of the virus with a high…