Ehsan Aghazadeh

11 papers Journal 8Unranked 3
YearRankTypeTitle / Venue / Authors
2025 J jnl
A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models.
CoRR
Liqiang Jing, Guiming Hardy Chen, Ehsan Aghazadeh, Xin Eric Wang, Xinya Du
2025 J jnl
CGES: Confidence-Guided Early Stopping for Efficient and Accurate Self-Consistency.
CoRR
Ehsan Aghazadeh, Ahmad Ghasemi, Hedyeh Beyhaghi, Hossein Pishro-Nik
2024 J jnl
From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries.
CoRR
Hitesh Wadhwa, Rahul Seetharaman, Somyaa Aggarwal, Reshmi Ghosh, Samyadeep Basu, Soundararajan Srinivasan, Wenlong Zhao, Shreyas Chaudhari, Ehsan Aghazadeh
2024 J jnl
Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis.
CoRR
Reshmi Ghosh, Rahul Seetharaman, Hitesh Wadhwa, Somyaa Aggarwal, Samyadeep Basu, Soundararajan Srinivasan, Wenlong Zhao, Shreyas Chaudhari, Ehsan Aghazadeh
2023 — conf
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition.
ACL (1)
Ali Modarressi, Mohsen Fayyaz, Ehsan Aghazadeh, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar
2023 J jnl
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition.
CoRR
Ali Modarressi, Mohsen Fayyaz, Ehsan Aghazadeh, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar
2022 J jnl
BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning.
CoRR
Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Mohammad Taher Pilehvar, Yadollah Yaghoobzadeh, Samira Ebrahimi Kahou
2022 — conf
Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages.
ACL (1)
Ehsan Aghazadeh, Mohsen Fayyaz, Yadollah Yaghoobzadeh
2022 J jnl
Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages.
CoRR
Ehsan Aghazadeh, Mohsen Fayyaz, Yadollah Yaghoobzadeh
2021 — conf
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations.
BlackboxNLP@EMNLP
Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar
2021 J jnl
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations.
CoRR
Mohsen Fayyaz, Ehsan Aghazadeh, Ali Modarressi, Hosein Mohebbi, Mohammad Taher Pilehvar