Richard Yuanzhe Pang
25 papers · 2019–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Academic Marathon (6) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (8) π Cross-Pollinator (11)
π
Cross-Pollinator
(11)
π
Renaissance Researcher
(7)
πΊοΈ
Taxonomy Completionist
(64)
π§¬
Topic Evolution
π
Keyword Champion
(2)
ποΈ
Keyword Collector
(110)
π
Trend Setter
π
Century Club
(24)
β
The Questioner
(2)
π₯
Unstoppable
(7)
β‘
Prolific Year
(5)
Conferences
ACL (8)
EMNLP (5)
ICML (3)
ICLR (2)
IJCNLP (2)
NAACL (2)
NIPS (2)
EACL (1)
Top co-authors
Keywords
large language model
(4)
natural language understanding
(3)
paraphrase generation
(2)
neural network
(2)
sequence generation
(2)
language model
(2)
energy-based model
(2)
reinforcement learning
(2)
inference network
(2)
transformer model
(2)
style transfer
(2)
benchmark evaluation
(2)
reward modeling
(2)
dataset evaluation
(2)
textual style transfer
(2)
item response theory
(2)
knowledge distillation
(1)
mathematical reasoning
(1)
dataset creation
(1)
natural language processing
(1)
Papers
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following
ACL 2026
Self-Generated Critiques Boost Reward Modeling for Language Models
NAACL 2025
Self-Consistency Preference Optimization
ICML 2025
Transformers Struggle to Learn to Search
ICLR 2025
Self-Rewarding Language Models
ICML 2024
Leveraging Implicit Feedback from Deployment Data in Dialogue
EACL 2024
Iterative Reasoning Preference Optimization
NIPS 2024
Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples
NIPS 2023
Reward Gaming in Conditional Text Generation
ACL 2023
What Do NLP Researchers Believe? Results of the NLP Community Metasurvey
ACL 2023
Extrapolative Controlled Sequence Generation via Iterative Refinement
ICML 2023
Token Dropping for Efficient BERT Pretraining
ACL 2022
SQuALITY: Building a Long-Document Summarization Dataset the Hard Way
EMNLP 2022
QuALITY: Question Answering with Long Input Texts, Yes!
NAACL 2022
Text Generation by Learning from Demonstrations
ICLR 2021
Comparing Test Sets with Item Response Theory
ACL 2021
AgreeSum: Agreement-Oriented Multi-Document Summarization
ACL 2021
Comparing Test Sets with Item Response Theory
IJCNLP 2021
AgreeSum: Agreement-Oriented Multi-Document Summarization
IJCNLP 2021
ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
ACL 2020
Consistency of a Recurrent Language Model With Respect to Incomplete Decoding
EMNLP 2020
Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
EMNLP 2020
Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?
ACL 2020
Unsupervised Evaluation Metrics and Learning Criteria for Non-Parallel Textual Transfer
EMNLP 2019
Towards Actual (Not Operational) Textual Style Transfer Auto-Evaluation
EMNLP 2019