Peiyang Liu
7 papers · 2021–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (3) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (11) π§ Keyword Pioneer π£ Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
ACL (3)
EMNLP (2)
COLING (1)
NAACL (1)
Top co-authors
Keywords
information retrieval
(2)
supervised fine-tuning
(2)
embedding-based retrieval
(2)
text classification
(1)
text mining
(1)
label smoothing
(1)
monte carlo tree search
(1)
text retrieval
(1)
language model
(1)
reward model
(1)
soft label
(1)
task interference
(1)
out-of-domain generalization
(1)
parameter importance
(1)
model optimization
(1)
human preference
(1)
rejection sampling
(1)
label distribution
(1)
reasoning path
(1)
parameter isolation
(1)
Papers
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
ACL 2026
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning
ACL 2026
Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories
ACL 2026
Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling
EMNLP 2025
Label Smoothing for Text Mining
COLING 2022
QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval
NAACL 2021
Improving Embedding-based Large-scale Retrieval via Label Enhancement
EMNLP 2021