Megan Ung
6 papers · 2022–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (3) π Cross-Pollinator (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (23)
π£
Hot Topic Early Bird
Conferences
ACL (4)
EMNLP (1)
NAACL (1)
Top co-authors
Keywords
dialogue system
(2)
language model
(2)
online learning
(1)
preference alignment
(1)
question answering
(1)
text generation
(1)
bias detection
(1)
scalable oversight
(1)
reward-based learning
(1)
human judgment
(1)
reward learning
(1)
human feedback
(1)
supervised learning
(1)
pearson correlation
(1)
embedding space
(1)
data contamination
(1)
ai alignment
(1)
rejection sampling
(1)
social bia
(1)
benchmark evaluation
(1)
Papers
Arbiters of Ambivalence: Challenges of using LLMs in No-Consensus tasks
ACL 2025
Improving Model Evaluation using SMART Filtering of Benchmark Datasets
NAACL 2025
Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback
ACL 2023
Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts
ACL 2023
ROBBIE: Robust Bias Evaluation of Large Generative Language Models
EMNLP 2023
SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures
ACL 2022