Siyu An
7 papers · 2023–2026 · 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
(24)
Venues
Top co-authors
Research topics
Artificial Intelligence
(7)
Core AI
(7)
Deep Learning
(4)
Natural Language Processing
(4)
Machine Learning
(2)
Generation
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Computer Vision
(1)
Application Areas
(1)
Applications
(1)
Core Methods
(1)
Domain-Specific
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Keywords
large language model
(4)
role-playing agent
(2)
dialogue system
(2)
conversational ai
(1)
text generation
(1)
multimodal learning
(1)
video understanding
(1)
narrative understanding
(1)
machine reading comprehension
(1)
graph construction
(1)
reinforcement learning from human feedback
(1)
human preference alignment
(1)
retrieval-augmented generation
(1)
representation editing
(1)
representation space
(1)
automatic prompt optimization
(1)
conflict detection
(1)
preference dataset
(1)
length bia
(1)
key information extraction
(1)
Papers
Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG
ACL 2026
FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema
COLING 2025
RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following
ACL 2025
RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents
ACL 2025
Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing
ACL 2025
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
EMNLP 2024
VKIE: The Application of Key Information Extraction on Video Text
EMNLP 2023