Papers by Zheng Xin Yong

13 papers
Preference Tuning For Toxicity Mitigation Generalizes Across Languages (2024.findings-emnlp)

Copied to clipboard

Challenge: Detoxifying multilingual Large Language Models (LLMs) has become crucial due to their increasing global use.
Approach: They propose to use English preference tuning to study cross-lingual detoxification of LLMs.
Outcome: The proposed method reduces toxicity in multilingual LLMs by reducing the probability of mGPT-1.3B generating toxic continuations across 17 languages.
The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating It (2025.emnlp-main)

Copied to clipboard

Challenge: a systematic review of 300 publications reveals a language gap in LLM safety research . even high-resource non-English languages receive little attention, authors note .
Approach: They propose to focus on safety evaluation, training data generation, and crosslingual safety generalization based on their findings.
Outcome: The authors suggest that the field can develop more robust, inclusive safety practices for diverse global populations.
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts (2022.acl-demo)

Copied to clipboard

Challenge: PromptSource is a system for creating, sharing, and using natural language prompts . prompts are used to train and query language models in zero-shot learning settings .
Approach: PromptSource is a system for creating, sharing, and using natural language prompts . et al.: using prompts to train and query language models is emerging area in NLP . they propose a templating language for defining data-linked prompts, a user interface that iterates on prompt development .
Outcome: PromptSource is a system for creating, sharing, and using natural language prompts . it has a templating language for defining data-linked prompts and a community-driven set of guidelines .
What Language Model to Train if You Have One Million GPU Hours? (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent years have seen the advent of large language models characterized by emergent capabilities arising from sheer scale alone.
Approach: They propose to use a multilingual model to compare performance to the English-only model by ablation at the billion-parameter scale.
Outcome: The proposed model is based on a multilingual model and its performance against the English-only model.
Semi-supervised Deep Embedded Clustering with Anomaly Detection for Semantic Frame Induction (2020.lrec-1)

Copied to clipboard

Challenge: Empirical results show that definitions provide contextual information for representing and characterizing the frame membership of lexical units.
Approach: They propose a two-step frame induction process to remove lexical units that cannot fit into existing frames in Berkeley FrameNet.
Outcome: The proposed method outperforms state-of-the-art methods in both steps of the frame induction process.
Crosslingual Generalization through Multitask Finetuning (2023.acl-long)

Copied to clipboard

Challenge: Multitask prompted finetuning (MTF) has been shown to help large language models generalize to new tasks in a zero-shot setting, but so far explorations of MTF have focused on English data and models.
Approach: They apply multitask prompted finetuning to pretrained multilingual models and generate variants called BLOOMZ and mT0.
Outcome: The proposed models can generalize to non-English languages that have never been seen before.
Frame Shift Prediction (2022.lrec-1)

Copied to clipboard

Challenge: Frame shift is a cross-linguistic phenomenon in translation which results in corresponding pairs of linguistic material evoking different frames.
Approach: They propose a task to predict cross-linguistic frame-to-frame correspondence and propose auxiliary training to learn cross-lingual frame-by-frame correlation.
Outcome: The proposed task can learn cross-linguistic frame-to-frame correspondence and predict frame shifts in a Berkeley FrameNet-like configuration.
LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing word-to-word translations from labeled task data in low-resource languages have limited lexical overlap with task data.
Approach: They propose a method that generates low-resource-language classification task data at scale using bilingual lexicons.
Outcome: The proposed method improves on 17 low-resource languages with bilingual lexicons compared with existing models on sentiment analysis and topic classification tasks.
BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting (2023.acl-long)

Copied to clipboard

Challenge: Existing language adaptation strategies for multilingual models are limited to 46 languages . a new language is added to the model to improve zero-shot prompting performance .
Approach: They apply existing language adaptation strategies to BLOOM and benchmark its zero-shot prompting performance on eight new languages in a resource-constrained setting.
Outcome: The proposed model can be extended to other languages without incurring prohibitively large costs.
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks (2025.findings-naacl)

Copied to clipboard

Challenge: Recent advances in Large Language Models have sparked concerns about their safety.
Approach: They propose a method to identify safety-related information in the model parameter space . they propose to use a few adversarially chosen examples to fine-tune LLMs .
Outcome: The proposed method can break safety alignment in multilingual LLMs using a few examples . it also shows that the proposed method jailbreaks LLM models adapted to new languages .
SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages (2024.emnlp-main)

Copied to clipboard

Challenge: Southeast Asia (SEA) is home to over 1,300 indigenous languages and 671 million people . prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA .
Approach: They propose to provide a resource center that provides standardized corpora in nearly 1,000 SEA languages across three modalities.
Outcome: a new benchmark assesses the quality of AI models on 36 SEA languages across 13 tasks . the results highlight the importance of SEA as a culturally diverse region .
The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges (2023.findings-acl)

Copied to clipboard

Challenge: Code-Switching is a common phenomenon in written text and conversation . it is not so common to observe code-switching in spoken language and not in written language .
Approach: They present a systematic survey on code-switching research in natural language processing to understand the progress of the past decades and conceptualize the challenges and tasks on the topic.
Outcome: The proposed model combines linguistic theories and machine learning techniques to understand the code-switching phenomenon.
Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation (2023.findings-emnlp)

Copied to clipboard

Challenge: Multilingualism is widespread around the world and code-switching (CSW) is a common practice among different language pairs/tuples across locations and regions.
Approach: They propose to use existing CSW data sets to improve the representativeness of CSW datasets.
Outcome: The proposed model lacks representativeness due to location-based, socio-demographic and register variation in CSW data.

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