Parishad BehnamGhader — accepted AI-conference papers

2025

Exploiting Instruction-Following Retrievers for Malicious Information Retrieval

Parishad BehnamGhader, Nicholas Meade, Siva Reddy

ACL 2025finding

Instruction-following retrievers have been widely adopted alongside LLMs in real-world applications, but little work has investigated the safety risks surrounding their increasing search capabilities. We empirically study the ability of retrievers to satisfy malicious queries, both when used directl…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model

Parishad BehnamGhader, Santiago Miret, Siva Reddy

EMNLP 2023long findings

Augmenting pretrained language models with retrievers has shown promise in effectively solving common NLP problems, such as language modeling and question answering. In this paper, we evaluate the strengths and weaknesses of popular retriever-augmented language models, namely kNN-LM, REALM, DPR + Fi…

Cited by 0 Source ↗code ↗Scholar ↗