Junru Lu
8 papers · 2020–2025 · 4 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(22)
Venues
Top co-authors
Research topics
Natural Language Processing
(6)
Artificial Intelligence
(5)
Machine Learning
(5)
Core AI
(5)
Applications
(4)
Generation
(3)
Learning Types
(3)
Deep Learning
(2)
Core Methods
(2)
Models
(2)
Application Areas
(1)
Learning Paradigms
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Resources & Methods
(1)
Keywords
large language model
(3)
question answering
(2)
direct preference optimization
(1)
machine reading comprehension
(1)
extractive summarization
(1)
chain-of-thought reasoning
(1)
preference optimization
(1)
human preference alignment
(1)
representation space
(1)
medical text
(1)
text simplification
(1)
reinforcement learning from human feedback
(1)
semantic similarity
(1)
generative model
(1)
semantic embedding
(1)
text generation
(1)
representation editing
(1)
role-playing agent
(1)
kl divergence
(1)
contrastive learning
(1)
Papers
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
Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing
ACL 2025
Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time
EMNLP 2025
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
EMNLP 2024
NapSS: Paragraph-level Medical Text Simplification via Narrative Prompting and Sentence-matching Summarization
EACL 2023
Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation
EMNLP 2022
CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering
COLING 2020