42 citations · 110 across the 36 of their papers we have counts for
40 papers
Interventional Training Reduces Causal Bypass in In-Context Introspection
Zilu Tang, Jongin Kim, Kerem Sahin +3
Introspection, the ability of a system to access and reason about its internal signals, is crucial for language model (LM) self-consistency and scalable interpretability. Prior wor…
DriveThru: a Document Extraction Platform and Benchmark Datasets for Indonesian Local Language Archives
Mohammad Rifqi Farhansyah, Muhammad Zuhdi Fikri Johari, Afinzaki Amiral +3
Indonesia is one of the most diverse countries linguistically. However, despite this linguistic diversity, Indonesian languages remain underrepresented in Natural Language Processi…
MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration
David Anugraha, Garry Kuwanto, Lucky Susanto +2
We present MetaMetrics-MT, an innovative metric designed to evaluate machine translation (MT) tasks by aligning closely with human preferences through Bayesian optimization with Ga…
Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models
Garry Kuwanto, Chaitanya Agarwal, Genta Indra Winata +1
Code-switching, the phenomenon of alternating between two or more languages in a single conversation, presents unique challenges for Natural Language Processing (NLP). Most existin…
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan +48
Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate th…
MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences
Genta Indra Winata, David Anugraha, Lucky Susanto +2
Understanding the quality of a performance evaluation metric is crucial for ensuring that model outputs align with human preferences. However, it remains unclear how well each metr…
Generating Faithful and Salient Text from Multimodal Data
Tahsina Hashem, Weiqing Wang, Derry Tanti Wijaya +2
While large multimodal models (LMMs) have obtained strong performance on many multimodal tasks, they may still hallucinate while generating text. Their performance on detecting sal…
Mitigating Translationese in Low-resource Languages: The Storyboard Approach
Garry Kuwanto, Eno-Abasi E. Urua, Priscilla Amondi Amuok +21
Low-resource languages often face challenges in acquiring high-quality language data due to the reliance on translation-based methods, which can introduce the translationese effect…
Enhancing Emotion Prediction in News Headlines: Insights from ChatGPT and Seq2Seq Models for Free-Text Generation
Ge Gao, Jongin Kim, Sejin Paik +5
Predicting emotions elicited by news headlines can be challenging as the task is largely influenced by the varying nature of people's interpretations and backgrounds. Previous work…
Detecting Frames in News Headlines and Lead Images in U.S. Gun Violence Coverage
Isidora Chara Tourni, Lei Guo, Hengchang Hu +9
News media structure their reporting of events or issues using certain perspectives. When describing an incident involving gun violence, for example, some journalists may focus on…
Learning Translations via Matrix Completion
Derry Wijaya, Brendan Callahan, John Hewitt +4
Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effectiv…
IndoToxic2024: A Demographically-Enriched Dataset of Hate Speech and Toxicity Types for Indonesian Language
Lucky Susanto, Musa Izzanardi Wijanarko, Prasetia Anugrah Pratama +4
Hate speech poses a significant threat to social harmony. Over the past two years, Indonesia has seen a ten-fold increase in the online hate speech ratio, underscoring the urgent n…
Could We Have Had Better Multilingual LLMs If English Was Not the Central Language?
Ryandito Diandaru, Lucky Susanto, Zilu Tang +2
Large Language Models (LLMs) demonstrate strong machine translation capabilities on languages they are trained on. However, the impact of factors beyond training data size on trans…
Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability
Afra Feyza Akyürek, Ekin Akyürek, Leshem Choshen +2
While language models (LMs) can sometimes generate factually correct text and estimate truth values of individual claims, these generally do not reflect a globally coherent, manipu…
An Empirical study of Unsupervised Neural Machine Translation: analyzing NMT output, model's behavior and sentences' contribution
Isidora Chara Tourni, Derry Wijaya
Unsupervised Neural Machine Translation (UNMT) focuses on improving NMT results under the assumption there is no human translated parallel data, yet little work has been done so fa…
Relevance-guided Neural Machine Translation
Isidora Chara Tourni, Derry Wijaya
With the advent of the Transformer architecture, Neural Machine Translation (NMT) results have shown great improvement lately. However, results in low-resource conditions still lag…
COVID-19 Vaccine Misinformation in Middle Income Countries
Jongin Kim, Byeo Rhee Bak, Aditya Agrawal +4
This paper introduces a multilingual dataset of COVID-19 vaccine misinformation, consisting of annotated tweets from three middle-income countries: Brazil, Indonesia, and Nigeria.…
DUnE: Dataset for Unified Editing
Afra Feyza Akyürek, Eric Pan, Garry Kuwanto +1
Even the most advanced language models remain susceptible to errors necessitating to modify these models without initiating a comprehensive retraining process. Model editing refers…
Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations
Zilu Tang, Mayank Agarwal, Alex Shypula +4
This work explores the use of self-generated natural language explanations as an intermediate step for code-to-code translation with language models. Across three types of explanat…
Replicable Benchmarking of Neural Machine Translation (NMT) on Low-Resource Local Languages in Indonesia
Lucky Susanto, Ryandito Diandaru, Adila Krisnadhi +2
Neural machine translation (NMT) for low-resource local languages in Indonesia faces significant challenges, including the need for a representative benchmark and limited data avai…
A Novel Method for Analysing Racial Bias: Collection of Person Level References
Muhammed Yusuf Kocyigit, Anietie Andy, Derry Wijaya
Long term exposure to biased content in literature or media can significantly influence people's perceptions of reality, leading to the development of implicit biases that are diff…
Generating Faithful Text From a Knowledge Graph with Noisy Reference Text
Tahsina Hashem, Weiqing Wang, Derry Tanti Wijaya +2
Knowledge Graph (KG)-to-Text generation aims at generating fluent natural-language text that accurately represents the information of a given knowledge graph. While significant pro…
RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs
Afra Feyza Akyürek, Ekin Akyürek, Aman Madaan +4
Despite their unprecedented success, even the largest language models make mistakes. Similar to how humans learn and improve using feedback, previous work proposed providing langua…
AugCSE: Contrastive Sentence Embedding with Diverse Augmentations
Zilu Tang, Muhammed Yusuf Kocyigit, Derry Wijaya
Data augmentation techniques have been proven useful in many applications in NLP fields. Most augmentations are task-specific, and cannot be used as a general-purpose tool. In our…