activity
20212026
most citedBERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning

4 citations · 7 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

13 papers · 1 filter

cs.CL2026

Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions

Pedro Henrique Luz de Araujo, Michael A. Hedderich, Ali Modarressi +2

Persona-assigned large language models (LLMs) are used in domains such as education, healthcare, and sociodemographic simulation. Yet, they are typically evaluated only in short, s…

cs.CL2025

Steering MoE LLMs via Expert (De)Activation

Mohsen Fayyaz, Ali Modarressi, Hanieh Deilamsalehy +5

Mixture-of-Experts (MoE) in Large Language Models (LLMs) routes each token through a subset of specialized Feed-Forward Networks (FFN), known as experts. We present SteerMoE, a fra…

cs.CL2025

Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models

Ahmad Dawar Hakimi, Ali Modarressi, Philipp Wicke +1

Understanding how large language models (LLMs) acquire and store factual knowledge is crucial for enhancing their interpretability and reliability. In this work, we analyze the evo…

cs.CL2025

ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge

Zeinab Sadat Taghavi, Ali Modarressi, Yunpu Ma +1

Retrieval systems are central to many NLP pipelines, but often rely on surface-level cues such as keyword overlap and lexical semantic similarity. To evaluate retrieval beyond thes…

cs.CL2025

Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing

Raoyuan Zhao, Abdullatif Köksal, Ali Modarressi +2

The reliability of large language models (LLMs) is greatly compromised by their tendency to hallucinate, underscoring the need for precise identification of knowledge gaps within L…

cs.CL2025

Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence

Mohsen Fayyaz, Ali Modarressi, Hinrich Schuetze +1

Dense retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG). Since they often serve as the first step in these…