Xinzhe Juan
4 papers · 2025–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (2) π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (14) π Cross-Pollinator (12)
π
Renaissance Researcher
(5)
β
The Questioner
Conferences
EMNLP (3)
ACL (1)
Top co-authors
Keywords
direct preference optimization
(2)
mathematical reasoning
(1)
language model alignment
(1)
llm evaluation
(1)
ai safety
(1)
reinforcement learning from human feedback
(1)
tree search
(1)
reward model
(1)
risk assessment
(1)
best-of-n sampling
(1)
human preference alignment
(1)
inference-time alignment
(1)
reasoning verification
(1)
temporal consistency
(1)
psychological assessment
(1)
human-ai interaction
(1)
mental health
(1)
error identification
(1)
response truncation
(1)
large language model
(1)
Papers
Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?
ACL 2025
EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety
EMNLP 2025
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
EMNLP 2025
Temporal Consistency for LLM Reasoning Process Error Identification
EMNLP 2025