Papers by Xiaolei Huang
Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing work on document classification models mainly uses synthetic monolingual data without ground truth for author demographic attributes. |
| Approach: | They assemble and publish a multilingual Twitter corpus for the task of hate speech detection using inferred author demographic factors. |
| Outcome: | The results show that the classifiers learn human biases and can be discriminatory towards certain demographic groups. |
Modeling Temporality of Human Intentions by Domain Adaptation (D18-1)
Copied to clipboard
| Challenge: | Recent research shows that themes and words within a conversation change across time, whereas topics and the patient's attitude towards their willingness to change might shift. |
| Approach: | They propose a method that models the temporal factor by using domain adaptation on clinical dialogue corpora, Motivational Interviewing (MI). |
| Outcome: | The proposed method improves on a college alcoholism dataset using a bi-LSTM and topic model to learn language usage change across different time sessions. |
Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing classification models only consider the temporal variations of existing data . current models focus on English corpora, leaving time as domains unexplored . |
| Approach: | They propose a framework to generalize classifiers over time on four languages, English, Danish, French, and German. |
| Outcome: | The proposed framework can generalize classifiers over time on four languages, English, Danish, French, and German. |
Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification (2022.starsem-1)
Copied to clipboard
| Challenge: | Existing models for class imbalanced labels learn domain-invariant representations across domains and evaluate primarily on class-balanced data. |
| Approach: | They propose an unsupervised domain adaptation approach that leverages feature variants and imbalanced labels across domains to learn robust representations. |
| Outcome: | The proposed method can learn robust domain-invariant representations and adapt classifiers on imbalanced classes over domains. |
Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models (P19-1)
Copied to clipboard
| Challenge: | Recent studies show that document classifiers can become more stable over time when trained in ways that account for temporal variations. |
| Approach: | They propose a method for embedding diachronic word embedds into document classification models . they propose 'time-driven neural classification model' that accounts for temporal variations . |
| Outcome: | The proposed model can be trained on six corpora and make it more robust over time. |
Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies either overlook temporal shifts or hardly capture rich shifting patterns of both semantic and knowledge. |
| Approach: | They develop a temporal adaptive learning framework that captures temporal shifts . they use medical ontology and other knowledge sources to integrate temporal adaptation . |
| Outcome: | The proposed framework improves classification tasks across multiple domains and domains with knowledge integration. |
Model-Agnostic Meta Learning for Class Imbalance Adaptation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to address class imbalance and data difficulty have been used to train models. |
| Approach: | They propose a framework that prioritizes challenging samples and minority classes over hard examples and their semantically similar neighbors to address class imbalance. |
| Outcome: | The proposed framework outperforms baselines on six imbalanced datasets and achieves substantial improvements for minority classes. |
Bhaasha, Bhāṣā, Zaban: A Survey for Low-Resourced Languages in South Asia – Current Stage and Challenges (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a survey examines the current efforts and challenges of NLP models for South Asian languages . there are more than 650 languages in South Asia, but many have very limited computational resources or are missing from existing models. |
| Approach: | a survey examines efforts and challenges of NLP for South Asian languages . they focus on transformer-based models such as BERT, T5, & GPT . findings highlight substantial issues, including missing data in critical domains . |
| Outcome: | The findings highlight significant issues, including missing data in critical domains . the survey aims to raise awareness within the NLP community for more targeted data curation . |
Length-Aware Multi-Kernel Transformer for Long Document Classification (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing SOTA models segment long texts into equal-length snippets, but they have new challenges of context fragmentation and generalizability due to sentence boundaries and varying text lengths. |
| Approach: | They propose a Length-Aware Multi-Kernel Transformer to encode long documents by transformers and vectorize text length by the kernels to promote model robustness over varying document lengths. |
| Outcome: | The proposed model outperforms existing models on five benchmarks from health and law domains up to an absolute 10.9% improvement. |
What Matters for Neural Cross-Lingual Named Entity Recognition: An Empirical Analysis (D19-1)
Copied to clipboard
| Challenge: | Named entity recognition models are challenging for languages with little training data. |
| Approach: | They propose a simple and efficient neural architecture for cross-lingual named entity recognition models. |
| Outcome: | The proposed model achieves competitive performance with the state-of-the-art on two transferable factors: sequential order and multilingual embedding. |
Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classification (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined. |
| Approach: | They propose a standard domain adaptation model to reduce gender bias in multilingual contexts. |
| Outcome: | The proposed model reduces gender bias and improves on two text classification tasks with three fair-aware baselines. |
Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Genetic Prompt combines genetic algorithms with Large Language Models to augment synthetic data generation. |
| Approach: | They propose a framework that combines genetic algorithms with LLMs to augment synthetic data generation. |
| Outcome: | The proposed framework outperforms state-of-the-art models and shows robust performance across generator models. |
Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models (2024.acl-long)
Copied to clipboard
Tianyi Tang, Wenyang Luo, Haoyang Huang, Dongdong Zhang, Xiaolei Wang, Xin Zhao, Furu Wei, Ji-Rong Wen
| Challenge: | Despite the impressive multilingual capabilities demonstrated by LLMs, the understanding of how these abilities develop and function remains nascent. |
| Approach: | They propose a novel detection method to pinpoint language-specific neurons within LLMs by selectively activating or deactivating these neurons. |
| Outcome: | The proposed method can “steer” the output language of LLMs by selectively activating or deactivating language-specific neurons. |
Towards Building More Robust NER datasets: An Empirical Study on NER Dataset Bias from a Dataset Difficulty View (2023.emnlp-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) models rely on superficial entity patterns for predictions, without considering evidence from the context. |
| Approach: | They propose to de-bias NER datasets by altering entity-context distribution . they also validate the feasibility of the proposed de-bianking techniques . |
| Outcome: | The proposed methods can be applied to different models and improve existing models. |
What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for instruction-tuning data contain redundancy and low-quality samples. |
| Approach: | They propose an instruction data selection framework based on weighted in-context influence . they show that sample difficulty negatively correlates with in-constext influence. |
| Outcome: | The proposed method outperforms baselines under constrained data budgets while demonstrating that sample difficulty negatively correlates with in-context influence. |
Examining Temporality in Document Classification (P18-2)
Copied to clipboard
| Challenge: | a recent study examines how document classification models trained during one time period perform on documents trained during other time periods. |
| Approach: | They propose to use a domain adaptation approach to adjust for changes in time to improve document classification. |
| Outcome: | The proposed model improves on documents trained on time intervals even on future time interval intervals. |