Letian Peng
17 papers · 2023–2026 · 6 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (42) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π€ Dynamic Duo (13)
β‘
Prolific Year Β· Productive
β
The Questioner
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(94)
Top co-authors
Research topics
Machine Learning
(12)
Natural Language Processing
(12)
Artificial Intelligence
(11)
Core AI
(8)
Core Methods
(8)
Applications
(7)
Generation
(7)
Learning Types
(6)
Deep Learning
(3)
Learning Paradigms
(3)
Optimization & Theory
(3)
Resources & Methods
(3)
Understanding
(2)
Application Areas
(1)
Architectures
(1)
Keywords
large language model
(6)
text generation
(4)
text classification
(3)
instruction following
(3)
semantic similarity
(3)
few-shot learning
(3)
data augmentation
(2)
constraint satisfaction
(2)
representation learning
(2)
weak supervision
(2)
cross-lingual transfer
(1)
information extraction
(1)
hierarchical classification
(1)
question answering
(1)
natural language inference
(1)
weakly supervised learning
(1)
sentiment analysis
(1)
knowledge probing
(1)
pseudo labeling
(1)
direct preference optimization
(1)
Papers
Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection
ACL 2026
C-World: A Computer Use Agent Environment Creator
ACL 2026
Deriving Character Logic from Storyline as Codified Decision Trees
ACL 2026
Correlation and Navigation in the Vocabulary Key Representation Space of Language Models
ICLR 2025
Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLMβs Nest
ACL 2025
The Price of Format: Diversity Collapse in LLMs
EMNLP 2025
ULTRABENCH: Benchmarking LLMs under Extreme Fine-grained Text Generation
EMNLP 2025
Answer is All You Need: Instruction-following Text Embedding via Answering the Question
ACL 2024
Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation
ACL 2024
Incubating Text Classifiers Following User Instruction with Nothing but LLM
EMNLP 2024
Learn from Failure: Fine-tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving
ACL 2024
Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
NeurIPS 2024
Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification
EMNLP 2024
Chride at SemEval-2023 Task 10: Fine-tuned Deberta-V3 on Detection of Online Sexism with Hierarchical Loss
SemEval 2023
Contextualized Semantic Distance between Highly Overlapped Texts
ACL 2023
iRe2f: Rethinking Effective Refinement in Language Structure Prediction via Efficient Iterative Retrospecting and Reasoning
IJCAI 2023
Less than One-shot: Named Entity Recognition via Extremely Weak Supervision
EMNLP 2023