Hengwei Liu
4 papers · 2025–2026 · 2 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 · Bronze
🗺️
Taxonomy Completionist
(11)
Top co-authors
Research topics
Keywords
large language model
(3)
outline generation
(2)
text generation
(1)
knowledge base
(1)
retrieval-augmented generation
(1)
automated evaluation
(1)
relational schema
(1)
long-form generation
(1)
instruction synthesis
(1)
group relative policy optimization
(1)
domain-specific benchmark
(1)
task discovery
(1)
database understanding
(1)
socratic prompting
(1)
refinement policy
(1)
reinforcement learning
(1)
structure-aware reward
(1)
self-supervised learning
(1)
Papers
AutoTaskEval: Towards Domain-Specific and Fine-Grained Evaluation for LLMs
ACL 2026
Leveraging Outline-Optimized Generative Interactions and Critique for Self-Refining Outlines with Reinforcement Learning
ACL 2026
DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL
EMNLP 2025
Logic: Long-form Outline Generation via Imitative and Critical Self-refinement
EMNLP 2025