Papers by Zilu Tang
A Multi-Labeled Dataset for Indonesian Discourse: Examining Toxicity, Polarization, and Demographics Information (2025.findings-acl)
Copied to clipboard
Lucky Susanto, Musa Izzanardi Wijanarko, Prasetia Anugrah Pratama, Zilu Tang, Fariz Akyas, Traci Hong, Ika Karlina Idris, Alham Fikri Aji, Derry Tanti Wijaya
| Challenge: | Prior research has focused on toxicity and polarization as separate problems . extreme polarizing deepens divisions, often leading to hostility and fragmentation . |
| Approach: | They propose to use a multi-label Indonesian dataset annotated for toxicity, polarization, and annotator demographic information to study polarizing language and toxicity. |
| Outcome: | The proposed dataset shows that polarization cues improve toxicity classification and vice versa. |
Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization (2025.naacl-long)
Copied to clipboard
| Challenge: | Machine Translation (MT) systems based on fine-tuned large language models (LLMs) are at a higher risk of generating hallucinations, which can severely undermine user’s trust and safety. |
| Approach: | They propose a method that intrinsically learns to mitigate hallucinations during the model training phase. |
| Outcome: | The proposed method reduces hallucinations by 89% on an average across three unseen target languages while preserving translation quality. |
Disentangling Text and Math in Word Problems: Evidence for the Bidimensional Structure of Large Language Models’ Reasoning (2025.findings-acl)
Copied to clipboard
Pedro Calais, Gabriel Franco, Zilu Tang, Themistoklis Nikas, Wagner Meira Jr., Evimaria Terzi, Mark Crovella
| Challenge: | Existing studies show that LLMs struggle with text interpretation and equation solving, despite distinct proficiencies in textual and mathematical components. |
| Approach: | They disentangle textual interpretation and mathematical solving steps in word problems drawn from Brazil's largest college entrance exam and popular grade school-level benchmark GSM8K. |
| Outcome: | The proposed model outperforms LLMs in Brazil's largest college entrance exam and popular grade school-level benchmark. |
AugCSE: Contrastive Sentence Embedding with Diverse Augmentations (2022.aacl-main)
Copied to clipboard
| Challenge: | Similar work has shown that a single augmentation can be used to learn a robust generalpurpose representation with contrastive learning. |
| Approach: | They propose a unified framework to utilize diverse sets of data augmentations to achieve a better, general-purpose sentence embedding model. |
| Outcome: | The proposed framework achieves state-of-the-art results on downstream transfer tasks and performs competitively on semantic textual similarity tasks, using only unsupervised data. |
Explain-then-translate: an analysis on improving program translation with self-generated explanations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Using self-generated natural language explanations improves zero-shot performance by 12% on average. |
| Approach: | They propose to use self-generated natural language explanations as an intermediate step for code-to-code translation with language models. |
| Outcome: | The proposed approach improves zero-shot performance by 12% on average . the proposed approach is not evaluated on a broader set of languages including low-resource languages. |