Yanzheng Xiang
8 papers · 2021–2025 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(26)
🔥
Unstoppable · Bronze
❓
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(7)
Natural Language Processing
(6)
Deep Learning
(5)
Core Methods
(4)
Learning Types · Machine Learning
(4)
Learning Types · Deep Learning
(4)
Artificial Intelligence
(3)
Applications · Natural Language Processing
(3)
Core AI
(3)
Generation
(3)
Optimization & Theory
(2)
Computer Science
(1)
Applications · Computer Science
(1)
Architectures
(1)
Models
(1)
Keywords
representation learning
(2)
large language model
(2)
in-context learning
(2)
contrastive learning
(2)
neural network interpretability
(1)
source code
(1)
preference alignment
(1)
flowchart parsing
(1)
knowledge distillation
(1)
program synthesis
(1)
code generation
(1)
graph structure
(1)
mechanistic interpretability
(1)
knowledge graph
(1)
pre-trained model
(1)
semantic parsing
(1)
pre-trained language model
(1)
retrieval-augmented generation
(1)
multi-hop reasoning
(1)
text classification
(1)
Papers
PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA
ACL 2025
Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language Models
ACL 2024
Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective
EMNLP 2024
The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis
EMNLP 2024
G3R: A Graph-Guided Generate-and-Rerank Framework for Complex and Cross-domain Text-to-SQL Generation
ACL 2023
Code Generation From Flowcharts with Texts: A Benchmark Dataset and An Approach
EMNLP 2022
Complicate Then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification
COLING 2022
A Divide-And-Conquer Approach for Multi-label Multi-hop Relation Detection in Knowledge Base Question Answering
EMNLP 2021