← Authors

Mehdi Rezagholizadeh

59 papers · 2019–2025 · 11 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (12) 🧭 Keyword Pioneer 🌍 Conference Polyglot (11) πŸƒ Academic Marathon (6) 🐝 Cross-Pollinator (14) 🏠 Conference Loyalist (20) 🀝 Dynamic Duo (18) πŸ”¬ Deep Specialist (22) πŸ† Keyword Champion (2) πŸ”₯ Unstoppable (7) πŸ“ˆ Trend Setter πŸ’Ž Century Club (59) πŸ—ƒοΈ Keyword Collector (212) ❓ The Questioner (3) ⚑ Prolific Year (14)

Conferences

EMNLP (20) ACL (15) EACL (6) NAACL (6) COLING (3) IJCNLP (3) AAAI (2) CONLL (1) IJCAI (1) INTERSPEECH (1) UAI (1)

Top co-authors

Ahmad Rashid (18) Ali Ghodsi (17) Abbas Ghaddar (16) Boxing Chen (12) Ivan Kobyzev (12) Phillippe Langlais (9) Prasanna Parthasarathi (8) Peng Lu (8) Qun Liu (8) Aref Jafari (7)

Keywords

knowledge distillation (23) model compression (20) large language model (10) pre-trained language model (6) adversarial training (5) language model (5) transformer architecture (4) masked language model (4) neural network (4) intermediate layer (4) neural machine translation (4) natural language understanding (4) attention mechanism (4) text generation (4) transfer learning (3) few-shot learning (3) pretrained language model (3) domain generalization (2) dependency parsing (2) model architecture (2)

Papers

Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models EMNLP 2025
Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination ACL 2025
ReGLA: Refining Gated Linear Attention NAACL 2025
CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search EMNLP 2024
Efficient Citer: Tuning Large Language Models for Enhanced Answer Quality and Verification NAACL 2024
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference EACL 2024
QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning EMNLP 2024
Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models EMNLP 2024
EWEK-QA : Enhanced Web and Efficient Knowledge Graph Retrieval for Citation-based Question Answering Systems ACL 2024
Resonance RoPE: Improving Context Length Generalization of Large Language Models ACL 2024
CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems ACL 2024
OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection ACL 2024
Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models IJCAI 2024
β€œKnowing When You Don’t Know”: A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation EMNLP 2024
Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity EMNLP 2024
DyLoRA: Parameter-Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation EACL 2023
Efficient Classification of Long Documents via State-Space Models EMNLP 2023
Practical Takes on Federated Learning with Pretrained Language Models EACL 2023
Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models EMNLP 2023
On the utility of enhancing BERT syntactic bias with Token Reordering Pretraining EMNLP 2023
Evaluating Embedding APIs for Information Retrieval ACL 2023
Attribute Controlled Dialogue Prompting ACL 2023
AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing ACL 2023
LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization ACL 2023
On the utility of enhancing BERT syntactic bias with Token Reordering Pretraining CONLL 2023
Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation EACL 2023
Do we need Label Regularization to Fine-tune Pre-trained Language Models? EACL 2023
Learning functions on multiple sets using multi-set transformers UAI 2022
From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables AAAI 2022
Kronecker Decomposition for GPT Compression ACL 2022
When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation ACL 2022
CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation COLING 2022
Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher COLING 2022
Dynamic Position Encoding for Transformers COLING 2022
Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing EMNLP 2022
Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging EMNLP 2022
Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization EMNLP 2022
KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation NAACL 2022
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation NAACL 2022
RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillation EMNLP 2021
Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation EMNLP 2021
Towards Zero-Shot Knowledge Distillation for Natural Language Processing EMNLP 2021
Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax IJCNLP 2021
Transformer-Based ASR Incorporating Time-Reduction Layer and Fine-Tuning with Self-Knowledge Distillation INTERSPEECH 2021
Knowledge Distillation with Noisy Labels for Natural Language Understanding EMNLP 2021
ALP-KD: Attention-Based Layer Projection for Knowledge Distillation AAAI 2021
MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation ACL 2021
How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding EMNLP 2021
Annealing Knowledge Distillation EACL 2021
Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax ACL 2021
End-to-End Self-Debiasing Framework for Robust NLU Training ACL 2021
MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation IJCNLP 2021
End-to-End Self-Debiasing Framework for Robust NLU Training IJCNLP 2021
Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition EMNLP 2020
Fully Quantized Transformer for Machine Translation EMNLP 2020
Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers EMNLP 2020
EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing ACL 2019
Bilingual-GAN: A Step Towards Parallel Text Generation NAACL 2019
Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation NAACL 2019