Lucas Dixon
20 papers · 2018–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
đ Cross-Pollinator (13) đ Academic Marathon (7) đ§ Keyword Pioneer đ Conference Polyglot (8) đ Renaissance Researcher (6)
đ
Conference Polyglot
(8)
đ
Academic Marathon
(7)
đ
Renaissance Researcher
(6)
đĨ
Mega-Team
(27)
đ¤
Dynamic Duo
(10)
đ§Ŧ
Topic Evolution
đ
Century Club
(20)
đ
Trend Setter
â
The Questioner
(2)
âĄ
Prolific Year
(5)
đī¸
Keyword Collector
(81)
đĨ
Unstoppable
(8)
Conferences
EMNLP (5)
ACL (4)
ICML (4)
NIPS (2)
SEMEVAL (2)
COLING (1)
EACL (1)
ICLR (1)
Top co-authors
Research topics
Keywords
text classification
(8)
toxicity detection
(4)
large language model
(3)
content moderation
(3)
parameter-efficient tuning
(2)
few-shot learning
(2)
prompt tuning
(2)
self-supervised learning
(1)
text style transfer
(1)
binary classification
(1)
sparse activation
(1)
harmful content
(1)
context modeling
(1)
hierarchical model
(1)
sentiment analysis
(1)
mixture of expert
(1)
lora fine-tuning
(1)
offensive language detection
(1)
language model
(1)
offline learning
(1)
Papers
To Mask or to Mirror: Human-AI Alignment in Collective Reasoning
EMNLP 2025
Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL
EMNLP 2025
Scalable Influence and Fact Tracing for Large Language Model Pretraining
ICLR 2025
Decoding-time Realignment of Language Models
ICML 2024
Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
COLING 2024
Interpretability Illusions in the Generalization of Simplified Models
ICML 2024
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
ICML 2024
Who's asking? User personas and the mechanics of latent misalignment
NIPS 2024
JUAGE at SemEval-2023 Task 10: Parameter Efficient Classification
SEMEVAL 2023
JUAGE at SemEval-2023 Task 10: Parameter Efficient Classification
ACL 2023
Harmful Language Datasets: An Assessment of Robustness
ACL 2023
Towards Agile Text Classifiers for Everyone
EMNLP 2023
Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis
NIPS 2022
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
ICML 2022
Civil Rephrases Of Toxic Texts With Self-Supervised Transformers
EACL 2021
Toxicity Detection: Does Context Really Matter?
ACL 2020
Six Attributes of Unhealthy Conversations
EMNLP 2020
ConvAI at SemEval-2019 Task 6: Offensive Language Identification and Categorization with Perspective and BERT
SEMEVAL 2019
Conversations Gone Awry: Detecting Early Signs of Conversational Failure
ACL 2018
WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community
EMNLP 2018