Pietro Lesci
7 papers · 2023–2025 · 4 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
(20)
Top co-authors
Research topics
Artificial Intelligence
(4)
Machine Learning
(4)
Core AI
(4)
Natural Language Processing
(3)
Core Methods
(3)
Optimization & Theory · Machine Learning
(3)
Deep Learning
(2)
Architectures
(2)
Learning Types · Machine Learning
(2)
Models
(2)
Resources & Methods
(2)
Applications
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
language model
(5)
training dynamics
(2)
causal inference
(2)
attention mechanism
(1)
question answering
(1)
convergence analysis
(1)
model analysis
(1)
dialogue state tracking
(1)
computational efficiency
(1)
scaling law
(1)
imbalanced classification
(1)
training stability
(1)
model scaling
(1)
downstream performance
(1)
zero-shot prompting
(1)
slot filling
(1)
table operation
(1)
joint goal accuracy
(1)
small language model
(1)
preference fine-tuning
(1)
Papers
Causal Estimation of Tokenisation Bias
ACL 2025
PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
ICLR 2025
Self-Training Large Language Models for Tool-Use Without Demonstrations
NAACL 2025
AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets
NAACL 2024
Causal Estimation of Memorisation Profiles
ACL 2024
Tending Towards Stability: Convergence Challenges in Small Language Models
EMNLP 2024
Diable: Efficient Dialogue State Tracking as Operations on Tables
ACL 2023