Taylor Sorensen
12 papers · 2022–2025 · 5 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 ↓+3 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (24) 🌍 Conference Polyglot · Silver 🧭 Keyword Pioneer 🗃️ Keyword Collector (64)
❓
The Questioner
⚡
Prolific Year · Productive
💎
Century Club · Bronze
Top co-authors
Research topics
Artificial Intelligence
(9)
Machine Learning
(8)
Natural Language Processing
(8)
Core AI
(8)
Resources & Methods
(5)
Application Areas
(4)
Deep Learning
(3)
Core Methods
(3)
Generation
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(2)
Learning Paradigms
(1)
Models
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
large language model
(3)
language model
(3)
value alignment
(3)
knowledge distillation
(2)
pluralistic alignment
(2)
preference modeling
(2)
rating prediction
(1)
natural language processing
(1)
representation learning
(1)
paraphrase generation
(1)
mutual information
(1)
human decision-making
(1)
text generation
(1)
multi-task learning
(1)
foundation model
(1)
prompt engineering
(1)
knowledge graph
(1)
in-context learning
(1)
human value
(1)
zero-shot learning
(1)
Papers
Can Language Models Reason about Individualistic Human Values and Preferences?
ACL 2025
Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models
NAACL 2025
Opt-ICL at LeWiDi-2025: Maximizing In-Context Signal from Rater Examples via Meta-Learning
EMNLP 2025
Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It
ICML 2025
Value Profiles for Encoding Human Variation
EMNLP 2025
Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model
NAACL 2024
Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration
EMNLP 2024
Position: A Roadmap to Pluralistic Alignment
ICML 2024
Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties
AAAI 2024
NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation
EMNLP 2023
An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels
ACL 2022
Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models
EMNLP 2022