Alberto Testoni
22 papers · 2018–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
🏃 Academic Marathon (7) 🌍 Conference Polyglot (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (13)
🌈
Renaissance Researcher
(7)
🌍
Conference Polyglot
(6)
🏃
Academic Marathon
(7)
🤝
Dynamic Duo
(15)
👥
Mega-Team
(20)
🏆
Keyword Champion
(3)
💎
Century Club
(20)
⚡
Prolific Year
(6)
❓
The Questioner
(4)
🗃️
Keyword Collector
(94)
🔥
Unstoppable
(5)
Conferences
ACL (9)
EMNLP (5)
EACL (3)
COLING (2)
IJCNLP (2)
NAACL (1)
Top co-authors
Keywords
multimodal learning
(7)
dialogue system
(5)
visual dialogue
(5)
large language model
(4)
visual grounding
(3)
task success
(3)
question generation
(3)
spatial question
(3)
entity hallucination
(2)
multimodal encoder
(2)
direct preference optimization
(2)
dialogue history
(2)
visual question answering
(2)
uncertainty quantification
(2)
zero-shot learning
(2)
vision language model
(2)
multimodal conversation
(2)
model evaluation
(1)
question answering
(1)
visual processing
(1)
Papers
Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA
ACL 2026
Mind the Gap: Benchmarking LLM Uncertainty and Calibration with Specialty-Aware Clinical QA and Reasoning-Based Behavioural Features
EACL 2026
From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions
ACL 2025
LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks
ACL 2025
RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs
EMNLP 2025
Playpen: An Environment for Exploring Learning From Dialogue Game Feedback
EMNLP 2025
Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions
EACL 2024
Naming, Describing, and Quantifying Visual Objects in Humans and LLMs
ACL 2024
Don’t Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models
ACL 2024
Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain
EMNLP 2024
ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments
COLING 2022
Visually Grounded Follow-up Questions: a Dataset of Spatial Questions Which Require Dialogue History
ACL 2021
Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy
EMNLP 2021
The Interplay of Task Success and Dialogue Quality: An in-depth Evaluation in Task-Oriented Visual Dialogues
EACL 2021
“I’ve Seen Things You People Wouldn’t Believe”: Hallucinating Entities in GuessWhat?!
IJCNLP 2021
Visually Grounded Follow-up Questions: a Dataset of Spatial Questions Which Require Dialogue History
IJCNLP 2021
“I’ve Seen Things You People Wouldn’t Believe”: Hallucinating Entities in GuessWhat?!
ACL 2021
They Are Not All Alike: Answering Different Spatial Questions Requires Different Grounding Strategies
EMNLP 2020
Effective questions in referential visual dialogue
ACL 2020
On the role of effective and referring questions in GuessWhat?!
ACL 2020
Quantifiers in a Multimodal World: Hallucinating Vision with Language and Sound
NAACL 2019
Grounded Textual Entailment
COLING 2018