Ziwei Ji
36 papers · 2019–2025 · 12 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+13 more ↓ Show less ↑
🌍 Conference Polyglot (12) 🏃 Academic Marathon (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird
🧭
Keyword Pioneer
🌈
Renaissance Researcher
(7)
🌉
Interdisciplinary Bridge
🤝
Dynamic Duo
(19)
👑
Triple Crown
🏆
Keyword Champion
(3)
🏆
Grand Slam
👥
Mega-Team
(48)
🧬
Topic Evolution
💎
Century Club
(36)
🗃️
Keyword Collector
(126)
⚡
Prolific Year
(5)
🔥
Unstoppable
(7)
Conferences
ICLR (7)
ACL (5)
EMNLP (5)
NIPS (4)
AACL (3)
ICML (3)
IJCNLP (3)
COLT (2)
AAAI (1)
ALT (1)
EACL (1)
NAACL (1)
Top co-authors
Keywords
gradient descent
(5)
hallucination detection
(4)
convex optimization
(4)
hallucination reduction
(3)
large language model
(3)
object hallucination
(2)
representation learning
(2)
multi-hop reasoning
(2)
convergence rate
(2)
implicit bia
(2)
margin maximization
(2)
logistic regression
(2)
benchmark evaluation
(2)
natural language inference
(2)
dialogue generation
(2)
text generation
(2)
video retrieval
(2)
dual optimization
(2)
maximum margin
(2)
controllable generation
(2)
Papers
Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
EMNLP 2025
High-Dimension Human Value Representation in Large Language Models
NAACL 2025
Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA
ICLR 2025
HalluLens: LLM Hallucination Benchmark
ACL 2025
Think before you speak: Training Language Models With Pause Tokens
ICLR 2024
ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models
NIPS 2024
ANAH: Analytical Annotation of Hallucinations in Large Language Models
ACL 2024
Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models
ACL 2024
LLM Internal States Reveal Hallucination Risk Faced With a Query
EMNLP 2024
Contrastive Learning for Inference in Dialogue
EMNLP 2023
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
AACL 2023
Improving Query-Focused Meeting Summarization with Query-Relevant Knowledge
AACL 2023
RHO: Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding
ACL 2023
NusaCrowd: Open Source Initiative for Indonesian NLP Resources
ACL 2023
Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training
EACL 2023
Towards Mitigating LLM Hallucination via Self Reflection
EMNLP 2023
Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference
ICML 2023
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
IJCNLP 2023
Improving Query-Focused Meeting Summarization with Query-Relevant Knowledge
IJCNLP 2023
VScript: Controllable Script Generation with Visual Presentation
IJCNLP 2022
VScript: Controllable Script Generation with Visual Presentation
AACL 2022
Actor-critic is implicitly biased towards high entropy optimal policies
ICLR 2022
Agnostic Learnability of Halfspaces via Logistic Loss
ICML 2022
Reproducibility in Optimization: Theoretical Framework and Limits
NIPS 2022
CrossNER: Evaluating Cross-Domain Named Entity Recognition
AAAI 2021
Characterizing the implicit bias via a primal-dual analysis
ALT 2021
Generalization bounds via distillation
ICLR 2021
Fast margin maximization via dual acceleration
ICML 2021
Early-stopped neural networks are consistent
NIPS 2021
Gradient descent follows the regularization path for general losses
COLT 2020
Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks
ICLR 2020
Neural tangent kernels, transportation mappings, and universal approximation
ICLR 2020
Multi-hop Question Generation with Graph Convolutional Network
EMNLP 2020
Directional convergence and alignment in deep learning
NIPS 2020
Gradient descent aligns the layers of deep linear networks
ICLR 2019
The implicit bias of gradient descent on nonseparable data
COLT 2019