Jonathan Bright
3 papers · 2024–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
NAACL (2)
COLING (1)
Top co-authors
Keywords
adversarial robustness
(1)
transfer learning
(1)
domain adaptation
(1)
text classification
(1)
cross-domain learning
(1)
adversarial training
(1)
abuse detection
(1)
adversarial attack
(1)
counterspeech generation
(1)
api interaction
(1)
abuse mitigation
(1)
asynchronous querying
(1)
llm endpoint
(1)
open source library
(1)
rate limit
(1)
Papers
Prompto: An open source library for asynchronous querying of LLM endpoints
NAACL 2025
DoDo Learning: Domain-Demographic Transfer in Language Models for Detecting Abuse Targeted at Public Figures
COLING 2024
On the Effectiveness of Adversarial Robustness for Abuse Mitigation with Counterspeech
NAACL 2024