Pedro Henrique Luz de Araujo
6 papers · 2022–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(15)
❓
The Questioner
Top co-authors
Research topics
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
Functionality learning through specification instructions
EMNLP 2024
Text-Guided Alternative Image Clustering
ACL 2024
Checking HateCheck: a cross-functional analysis of behaviour-aware learning for hate speech detection
ACL 2022