Pedro Henrique Luz de Araujo
6 papers · 2022–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (2) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (15) π§ Keyword Pioneer π Cross-Pollinator (15)
β
The Questioner
Conferences
ACL (3)
EMNLP (2)
EACL (1)
Top co-authors
Keywords
prompt engineering
(2)
hierarchical clustering
(1)
instruction following
(1)
instruction tuning
(1)
classification accuracy
(1)
image clustering
(1)
loss function
(1)
language model
(1)
vision-language model
(1)
model generalization
(1)
safety evaluation
(1)
robustness evaluation
(1)
behavioral testing
(1)
focal loss
(1)
confidence estimation
(1)
consensus clustering
(1)
hate speech detection
(1)
task performance
(1)
large language model
(1)
persona fidelity
(1)
Papers
Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions
EACL 2026
Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles
ACL 2025
Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance
EMNLP 2025
Text-Guided Alternative Image Clustering
ACL 2024
Functionality learning through specification instructions
EMNLP 2024
Checking HateCheck: a cross-functional analysis of behaviour-aware learning for hate speech detection
ACL 2022