Punyajoy Saha
14 papers · 2021–2025 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (25) π Interdisciplinary Bridge π Renaissance Researcher (6) π Conference Polyglot (10) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π
Conference Polyglot
(10)
π€
Dynamic Duo
(13)
β
The Questioner
β‘
Prolific Year
(5)
π
Century Club
(14)
π₯
Unstoppable
(5)
Conferences
COLING (3)
EACL (2)
EMNLP (2)
AAAI (1)
AACL (1)
ACL (1)
CONLL (1)
IJCAI (1)
IJCNLP (1)
NIPS (1)
Top co-authors
Keywords
hate speech detection
(7)
text classification
(7)
text generation
(5)
large language model
(4)
counterspeech generation
(3)
hate speech
(3)
transformer model
(3)
cross-lingual transfer
(2)
zero-shot learning
(2)
content moderation
(2)
transfer learning
(2)
romanized bengali
(2)
multilingual model
(2)
low-resource language
(2)
prompt engineering
(2)
indic language
(2)
model interpretability
(1)
neural architecture
(1)
bias detection
(1)
social media analysis
(1)
Papers
HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation
ACL 2025
Low-Resource Counterspeech Generation for Indic Languages: The Case of Bengali and Hindi
EACL 2024
CrowdCounter: A benchmark type-specific multi-target counterspeech dataset
CONLL 2024
CrowdCounter: A benchmark type-specific multi-target counterspeech dataset
EMNLP 2024
InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks
COLING 2024
On Zero-Shot Counterspeech Generation by LLMs
COLING 2024
Probing LLMs for hate speech detection: strengths and vulnerabilities
EMNLP 2023
Hate Speech and Offensive Language Detection in Bengali
IJCNLP 2022
Hate Speech and Offensive Language Detection in Bengali
AACL 2022
Which One Is More Toxic? Findings from Jigsaw Rate Severity of Toxic Comments
COLING 2022
CounterGeDi: A Controllable Approach to Generate Polite, Detoxified and Emotional Counterspeech
IJCAI 2022
Multilingual Abusive Comment Detection at Scale for Indic Languages
NIPS 2022
Hate-Alert@DravidianLangTech-EACL2021: Ensembling strategies for Transformer-based Offensive language Detection
EACL 2021
HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
AAAI 2021