Mark Dras
39 papers · 2000–2026 · 12 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Academic Marathon (25) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (11) π£ Hot Topic Early Bird
π
Conference Polyglot
(11)
π
Academic Marathon
(25)
π§
Keyword Pioneer
π§¬
Topic Evolution
ποΈ
Keyword Collector
(93)
π
Conference Pioneer
π
Century Club
(34)
π₯
Unstoppable
(8)
π
Trend Setter
β
The Questioner
(2)
Conferences
ACL (13)
EMNLP (7)
COLING (3)
EACL (3)
IJCNLP (3)
NAACL (3)
CONLL (2)
AAAI (1)
AACL (1)
IJCAI (1)
NIPS (1)
SEMEVAL (1)
Top co-authors
Research topics
Keywords
large language model
(6)
copy mechanism
(2)
constrained text generation
(2)
mixture of expert
(2)
natural language processing
(2)
text classification
(2)
dependency parsing
(2)
anomaly detection
(1)
few-shot learning
(1)
transformer architecture
(1)
sentiment analysis
(1)
hyperparameter optimization
(1)
named entity recognition
(1)
text generation
(1)
representation learning
(1)
model merging
(1)
language identification
(1)
structured prediction
(1)
responsible ai
(1)
word segmentation
(1)
Papers
Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA
AAAI 2026
When the Model Said βNo Commentβ, We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified
EACL 2026
SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering
ACL 2026
AlignCultura: Towards Culturally Aligned Large Language Models?
ACL 2026
Framing Political Bias in Multilingual LLMs Across Pakistani Languages
ACL 2026
VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare
ACL 2025
Too Helpful, Too Harmless, Too Honest or Just Right?
EMNLP 2025
Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients
EMNLP 2024
Hereβs a Free Lunch: Sanitizing Backdoored Models with Model Merge
ACL 2024
OptIForest: Optimal Isolation Forest for Anomaly Detection
IJCAI 2023
What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples
AACL 2023
What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples
IJCNLP 2023
Few-shot fine-tuning SOTA summarization models for medical dialogues
NAACL 2022
Detecting Textual Adversarial Examples Based on Distributional Characteristics of Data Representations
ACL 2022
Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation
NIPS 2021
Mention Flags (MF): Constraining Transformer-based Text Generators
ACL 2021
Mention Flags (MF): Constraining Transformer-based Text Generators
IJCNLP 2021
Large Scale Author Obfuscation Using Siamese Variational Auto-Encoder: The SiamAO System
COLING 2020
Predicting accuracy on large datasets from smaller pilot data
ACL 2018
VnCoreNLP: A Vietnamese Natural Language Processing Toolkit
NAACL 2018
A Novel Neural Network Model for Joint POS Tagging and Graph-based Dependency Parsing
CONLL 2017
Feature Hashing for Language and Dialect Identification
ACL 2017
Unsupervised Text Segmentation Based on Native Language Characteristics
ACL 2017
LTG at SemEval-2016 Task 11: Complex Word Identification with Classifier Ensembles
SEMEVAL 2016
Large-Scale Native Language Identification with Cross-Corpus Evaluation
NAACL 2015
Chinese Native Language Identification
EACL 2014
Language Transfer Hypotheses with Linear SVM Weights
EMNLP 2014
Working with a small dataset - semi-supervised dependency parsing for Irish
EMNLP 2013
Is Bad Structure Better Than No Structure?: Unsupervised Parsing for Realisation Ranking
COLING 2012
Exploring Adaptor Grammars for Native Language Identification
EMNLP 2012
Exploring Adaptor Grammars for Native Language Identification
CONLL 2012
Clause Restructuring For SMT Not Absolutely Helpful
ACL 2011
Exploiting Parse Structures for Native Language Identification
EMNLP 2011
Improving Grammaticality in Statistical Sentence Generation: Introducing a Dependency Spanning Tree Algorithm with an Argument Satisfaction Model
EACL 2009
Choosing the Right Translation: A Syntactically Informed Classification Approach
COLING 2008
Seed and Grow: Augmenting Statistically Generated Summary Sentences using Schematic Word Patterns
EMNLP 2008
GLEU: Automatic Evaluation of Sentence-Level Fluency
ACL 2007
Towards Statistical Paraphrase Generation: Preliminary Evaluations of Grammaticality
IJCNLP 2005
Multi-Component TAG and Notions of Formal Power
ACL 2000