Alisa Liu
16 papers · 2019–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Academic Marathon (6) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (6) π Cross-Pollinator (12)
π
Academic Marathon
(6)
π§
Keyword Pioneer
π
Cross-Pollinator
(12)
π₯
Unstoppable
(5)
π
Century Club
(15)
β
The Questioner
(2)
π
Trend Setter
ποΈ
Keyword Collector
(80)
Conferences
ACL (7)
EMNLP (3)
NAACL (2)
NIPS (2)
ICML (1)
IJCNLP (1)
Top co-authors
Research topics
Keywords
language model
(8)
large language model
(4)
product of expert
(3)
natural language inference
(2)
sentiment control
(2)
language detoxification
(2)
controlled text generation
(2)
commonsense reasoning
(2)
data augmentation
(2)
question answering
(2)
text detoxification
(2)
text generation
(2)
model merging
(1)
toxicity detection
(1)
preference learning
(1)
prompt engineering
(1)
dataset creation
(1)
semi-supervised learning
(1)
context modeling
(1)
sentiment analysis
(1)
Papers
When One LLM Drools, Multi-LLM Collaboration Rules
ACL 2026
LlamaPIE: Proactive In-Ear Conversation Assistants
ACL 2025
Synthetic Data in the Era of Large Language Models
ACL 2025
Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models
NAACL 2025
Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions
NIPS 2024
Decoding-Time Language Model Alignment with Multiple Objectives
NIPS 2024
How Language Model Hallucinations Can Snowball
ICML 2024
Self-Instruct: Aligning Language Models with Self-Generated Instructions
ACL 2023
Weβre Afraid Language Models Arenβt Modeling Ambiguity
EMNLP 2023
That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context?
EMNLP 2023
Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts
ACL 2023
WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation
EMNLP 2022
Generated Knowledge Prompting for Commonsense Reasoning
ACL 2022
DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts
ACL 2021
DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts
IJCNLP 2021
CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense
NAACL 2019