Patrick Kahardipraja
5 papers · 2020–2025 · 2 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
Top co-authors
Research topics
Natural Language Processing
(4)
Understanding
(4)
Deep Learning
(3)
Machine Learning
(2)
Architectures
(2)
Core Methods
(2)
Artificial Intelligence
(1)
Core AI
(1)
Learning Types
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
incremental processing
(3)
transformer model
(2)
language model
(2)
coreference resolution
(1)
probing analysis
(1)
sequence labelling
(1)
interpretability evaluation
(1)
latent representation
(1)
autoregressive model
(1)
mechanistic interpretability
(1)
sparse autoencoder
(1)
linear transformer
(1)
span representation
(1)
bidirectional encoder
(1)
automated interpretability
(1)
feature description
(1)
description evaluation
(1)
faithfulness metric
(1)
probing model
(1)
large language model
(1)
Papers
FADE: Why Bad Descriptions Happen to Good Features
ACL 2025
When Only Time Will Tell: Interpreting How Transformers Process Local Ambiguities Through the Lens of Restart-Incrementality
ACL 2024
TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Model
ACL 2023
Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU
EMNLP 2021
Exploring Span Representations in Neural Coreference Resolution
EMNLP 2020