Michael Hanna
15 papers · 2021–2025 · 8 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 ↓+7 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (26) 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 👥 Mega-Team · Squad
👥
Mega-Team · Squad
🗃️
Keyword Collector
(77)
📈
Trend Setter
❓
The Questioner
(3)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(12)
Core AI
(12)
Natural Language Processing
(8)
Deep Learning
(6)
Machine Learning
(6)
Resources & Methods
(6)
Learning Types
(4)
Understanding
(4)
Architectures
(3)
Interdisciplinary
(2)
Applications
(2)
Linguistics
(2)
Models
(2)
Optimization & Theory
(2)
Application Areas
(1)
Keywords
large language model
(5)
mechanistic interpretability
(4)
language model
(3)
lexical semantics
(2)
transformer language model
(2)
circuit analysis
(2)
sparse autoencoder
(2)
pre-trained language model
(2)
neural network
(2)
natural language understanding
(1)
embodied ai
(1)
visual reasoning
(1)
natural language inference
(1)
model analysis
(1)
benchmark evaluation
(1)
language model evaluation
(1)
knowledge probing
(1)
machine translation
(1)
bias mitigation
(1)
semantic similarity
(1)
Papers
Circuit-Tracer: A New Library for Finding Feature Circuits
EMNLP 2025
Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models
NAACL 2025
LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks
ACL 2025
MIB: A Mechanistic Interpretability Benchmark
ICML 2025
Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!
ACL 2024
LLM Circuit Analyses Are Consistent Across Training and Scale
NeurIPS 2024
Transformer-specific Interpretability
EACL 2024
ChapGTP, ILLC’s Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formation
CoNLL 2023
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model
NeurIPS 2023
Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model
EMNLP 2023
The Functional Relevance of Probed Information: A Case Study
EACL 2023
When Language Models Fall in Love: Animacy Processing in Transformer Language Models
EMNLP 2023
ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments
COLING 2022
A Fine-Grained Analysis of BERTScore
EMNLP 2021
Analyzing BERT’s Knowledge of Hypernymy via Prompting
EMNLP 2021