Papers by Xi Ai

8 papers
Are Knowledge and Reference in Multilingual Language Models Cross-Lingually Consistent? (2025.findings-emnlp)

Copied to clipboard

Challenge: Cross-lingual consistency should be considered to assess cross-lingual transferability, maintain factuality of model knowledge across languages, and preserve parity of language model performance.
Approach: They examine pretrained and tuned models with code-mixed coreferential statements that convey identical knowledge across languages.
Outcome: The proposed model shows different levels of consistency in multilingual models, subject to language families, linguistic factors, scripts, and bottlenecks on a particular layer.
On-the-fly Cross-lingual Masking for Multilingual Pre-training (2023.acl-long)

Copied to clipboard

Challenge: In multilingual pre-training, multilingual models only learn cross-linguality implicitly from isomorphic spaces formed by overlapping different language spaces due to the lack of explicit cross-linguistic forward pass.
Approach: They propose a dynamic token-wise masking scheme for multilingual pre-training that uses a special token [C]x to replace a random token in the input sentence.
Outcome: The proposed model improves the performance of UNMT models on De, Ro, Ne En.
TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies show that advanced LLMs produce text indistinguishable from human writing.
Approach: They propose a benchmark to assess persona simulation across diverse contexts by decomposing the evaluation into six fundamental capabilities including opinion consistency, memory recall, logical reasoning, persona tone, and syntactic style.
Outcome: The proposed model achieves moderate accuracy but falls short of the basic capabilities needed to simulate personas in real-world contexts.
Leveraging Relaxed Equilibrium by Lazy Transition for Sequence Modeling (2022.acl-long)

Copied to clipboard

Challenge: Using attention-based models, certain tokens are less ambiguous than others, and they require fewer refinements for disambiguation.
Approach: They propose a lazy transition mechanism to adjust the significance of iterative refinements for each token representation.
Outcome: The proposed model outperforms baseline models on several tasks with the same number of parameters.
Zero-shot Cross-lingual Alignment for Embedding Initialization (2024.findings-acl)

Copied to clipboard

Challenge: CrossInit initializes embeddings into similar geometrical structures across languages in unsupervised manner.
Approach: They propose a method that initializes embeddings into similar geometrical structures across languages in an unsupervised manner.
Outcome: The proposed method demostrates similar patterns in low-resource and dissimilar languages.
Vocabulary-informed Language Encoding (2022.coling-1)

Copied to clipboard

Challenge: A Multilingual model relies on language encodings to identify input languages . a method to compute a vocabulary-informed language coding can improve multilingual models .
Approach: They propose a method to compute a vocabulary-informed language encoding as the language representation for a required language.
Outcome: The proposed method improves performance on unsupervised translation and cross-lingual embedding.
Almost Free Semantic Draft for Neural Machine Translation (2021.naacl-main)

Copied to clipboard

Challenge: Empirical experiments show that the presented method can achieve competitive performance in common language pairs with a clear advantage in inference efficiency.
Approach: They propose a method to sample and consider a semantic draft as global information from semantic space for decoding with almost free of cost.
Outcome: Empirical results show that the proposed method can achieve competitive performance in common language pairs with a clear advantage in inference efficiency.
Multilingual Pre-training with Self-supervision from Global Co-occurrence Information (2023.findings-acl)

Copied to clipboard

Challenge: Empirical studies show multilinguality and crosslinguality emerge from MLM pretraining without supervision.
Approach: They propose to use global co-occurrence information as a source of structural information on multilingual corpora.
Outcome: Empirical studies show that MLM-GC pre-training outperforms MLM pre- training for 4 downstream cross-lingual tasks and 1 additional monolingual task.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations