Ali Modarressi
14 papers · 2021–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (38) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🏆
Keyword Champion
(2)
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
❓
The Questioner
(2)
💎
Century Club · Bronze
🗃️
Keyword Collector
(83)
Top co-authors
Research topics
Machine Learning
(13)
Artificial Intelligence
(10)
Core AI
(10)
Natural Language Processing
(9)
Deep Learning
(7)
Core Methods
(6)
Application Areas
(4)
Applications
(4)
Optimization & Theory · Machine Learning
(4)
Resources & Methods
(4)
Architectures
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Optimization & Theory · Deep Learning
(2)
Computer Science
(1)
Keywords
large language model
(3)
layer-wise analysis
(2)
attention mechanism
(2)
relation extraction
(2)
token attribution
(2)
gradient-based saliency
(2)
document-level extraction
(1)
syntactic analysis
(1)
transfer learning
(1)
knowledge probing
(1)
information retrieval
(1)
instruction following
(1)
model analysis
(1)
efficient computing
(1)
knowledge transfer
(1)
dense retrieval
(1)
language understanding
(1)
knowledge representation
(1)
cross-lingual alignment
(1)
linguistic knowledge
(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
Do We Know What LLMs Don’t Know? A Study of Consistency in Knowledge Probing
EMNLP 2025
ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge
EMNLP 2025
MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment
ACL 2025
NoLiMa: Long-Context Evaluation Beyond Literal Matching
ICML 2025
Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models
ACL 2025
Consistent Document-level Relation Extraction via Counterfactuals
EMNLP 2024
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
ACL 2023
Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities
EACL 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 BERToids’ Representations
EMNLP 2021