Ali Modarressi
14 papers · 2021–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
๐ Renaissance Researcher (5) ๐ Interdisciplinary Bridge ๐ Conference Polyglot (5) ๐ Academic Marathon (5) ๐บ๏ธ Taxonomy Completionist (38)
๐งญ
Keyword Pioneer
๐ฃ
Hot Topic Early Bird
๐
Conference Polyglot
(5)
๐
Keyword Champion
(2)
โก
Prolific Year
(6)
๐
Century Club
(13)
โ
The Questioner
๐ฅ
Unstoppable
(5)
๐๏ธ
Keyword Collector
(79)
Conferences
ACL (5)
EMNLP (5)
EACL (2)
ICML (1)
NAACL (1)
Top co-authors
Keywords
layer-wise analysis
(2)
gradient-based saliency
(2)
token attribution
(2)
relation extraction
(2)
large language model
(2)
document-level extraction
(1)
syntactic analysis
(1)
transfer learning
(1)
knowledge probing
(1)
information retrieval
(1)
knowledge transfer
(1)
instruction following
(1)
model analysis
(1)
efficient computing
(1)
language understanding
(1)
knowledge representation
(1)
linguistic knowledge
(1)
dense retrieval
(1)
cross-lingual alignment
(1)
out-of-distribution generalization
(1)
Papers
Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions
EACL 2026
Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence
ACL 2025
Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models
ACL 2025
MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment
ACL 2025
Do We Know What LLMs Donโt Know? A Study of Consistency in Knowledge Probing
EMNLP 2025
NoLiMa: Long-Context Evaluation Beyond Literal Matching
ICML 2025
ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge
EMNLP 2025
Consistent Document-level Relation Extraction via Counterfactuals
EMNLP 2024
Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities
EACL 2023
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
ACL 2023
AdapLeR: Speeding up Inference by Adaptive Length Reduction
ACL 2022
GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
NAACL 2022
Exploring the Role of BERT Token Representations to Explain Sentence Probing Results
EMNLP 2021
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToidsโ Representations
EMNLP 2021