Wenda Xu
16 papers · 2022–2026 · 6 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 ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (39) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π€ Dynamic Duo (11)
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(79)
Top co-authors
Research topics
Natural Language Processing
(15)
Artificial Intelligence
(11)
Core AI
(11)
Machine Learning
(8)
Generation
(7)
Deep Learning
(6)
Learning Types Β· Machine Learning
(5)
Applications
(4)
Learning Types Β· Deep Learning
(4)
Resources & Methods
(4)
Models
(2)
Optimization & Theory
(2)
Healthcare & Medicine
(1)
Knowledge & Reasoning
(1)
Speech & Audio
(1)
Keywords
text generation
(5)
large language model
(5)
evaluation metric
(3)
self-supervised learning
(2)
preference alignment
(2)
natural language generation
(2)
machine translation
(2)
language model
(2)
instruction following
(2)
text generation evaluation
(2)
text-to-image synthesis
(1)
conversational ai
(1)
model evaluation
(1)
dialogue generation
(1)
metric learning
(1)
natural language inference
(1)
mathematical reasoning
(1)
parallel corpus
(1)
multimodal learning
(1)
preference optimization
(1)
Papers
Generating Difficult-to-Translate Texts
EACL 2026
CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation
NAACL 2025
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
ICLR 2025
Uncovering Factor-Level Preference to Improve Human-Model Alignment
EMNLP 2025
BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment
EMNLP 2024
LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
NAACL 2024
Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement
ACL 2024
Translation Canvas: An Explainable Interface to Pinpoint and Analyze Translation Systems
EMNLP 2024
CausalDialogue: Modeling Utterance-level Causality in Conversations
ACL 2023
INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback
EMNLP 2023
Neuro-Symbolic Procedural Planning with Commonsense Prompting
ICLR 2023
PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers
EACL 2023
SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes
ACL 2023
Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
EACL 2023
Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis
EMNLP 2022
Self-Supervised Knowledge Assimilation for Expert-Layman Text Style Transfer
AAAI 2022