Wenda Xu
16 papers · 2022–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (38) π Interdisciplinary Bridge π Conference Polyglot (6) π Renaissance Researcher (7) π§ Keyword Pioneer
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π€
Dynamic Duo
(11)
β‘
Prolific Year
(6)
π
Century Club
(15)
π
Trend Setter
π₯
Unstoppable
(5)
ποΈ
Keyword Collector
(71)
Conferences
EMNLP (5)
ACL (3)
EACL (3)
ICLR (2)
NAACL (2)
AAAI (1)
Top co-authors
Keywords
large language model
(5)
text generation
(4)
evaluation metric
(3)
self-supervised learning
(2)
language model
(2)
natural language generation
(2)
preference alignment
(2)
machine translation
(2)
text generation evaluation
(2)
text-to-image synthesis
(1)
model evaluation
(1)
metric learning
(1)
dialogue generation
(1)
conversational ai
(1)
natural language inference
(1)
mathematical reasoning
(1)
instruction following
(1)
parallel corpus
(1)
language model alignment
(1)
multimodal learning
(1)
Papers
Generating Difficult-to-Translate Texts
EACL 2026
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
ICLR 2025
Uncovering Factor-Level Preference to Improve Human-Model Alignment
EMNLP 2025
CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation
NAACL 2025
BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment
EMNLP 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
LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
NAACL 2024
INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback
EMNLP 2023
CausalDialogue: Modeling Utterance-level Causality in Conversations
ACL 2023
Visualize Before You Write: Imagination-Guided Open-Ended Text Generation
EACL 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
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