Chiara Di Bonaventura
6 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(4)
🌉
Interdisciplinary Bridge
🗺️
Taxonomy Completionist
(12)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
ACL (3)
COLING (1)
EACL (1)
EMNLP (1)
Top co-authors
Keywords
benchmark evaluation
(1)
sentiment analysis
(1)
text classification
(1)
abusive language detection
(1)
offensive language detection
(1)
language model evaluation
(1)
explanation generation
(1)
explainable ai
(1)
model safety
(1)
support vector machine
(1)
bias mitigation
(1)
language model
(1)
human-ai interaction
(1)
user study
(1)
lexical feature
(1)
semantic change detection
(1)
gender bia
(1)
hate speech detection
(1)
diachronic analysis
(1)
semantic drift
(1)
Papers
Hatevolution: What Static Benchmarks Don’t Tell Us
ACL 2025
Wanted: Personalised Bias Warnings for Gender Bias in Language Models
ACL 2025
An Annotation Protocol for Diachronic Evaluation of Semantic Drift in Disability Sources
ACL 2025
From Detection to Explanation: Effective Learning Strategies for LLMs in Online Abusive Language Research
COLING 2025
ferret: a Framework for Benchmarking Explainers on Transformers
EACL 2023
Leveraging time-dependent lexical features for offensive language detection
EMNLP 2022