activity
20242026
collaborators

6 papers

cs.CL2026

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…

cs.CL2026

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…

cs.CL2025

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…

cs.LG2025

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…

cs.LG2024

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…

cs.CV2024

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…