1 citations · 4 across the 38 of their papers we have counts for
41 papers
Steering with Multilingual Lexicons for Sentiment Control in Low-Resource Languages
Lucinda Laurent, Muhammad Dehan Al Kautsar, Alfan Farizki Wicaksono +1
Activation steering offers a lightweight mechanism for controlling model behavior, but existing methods depend on sentence-level contrastive data that is unavailable for most of th…
Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close
Rania Elbadry, Ahmed Heakl, Saeed Almheiri +12
When a question has valid answers under different normative frameworks, a language model must decide which framework to use and whether it can answer correctly within it. We call t…
CultureTalk-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages
Muhammad Dehan Al Kautsar, Salsabila Pranida, Bilal Elbouardi +1
Culture is lived through conversation, yet existing Indonesian cultural commonsense benchmarks evaluate LLMs on short and isolated prompts, stripping away the dialogic context in w…
Jais 2: A Family of Arabic-Centric Open Large Language Models
Mohamed Anwar, Abed Alhakim Freihat, George Ibrahim +57
Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong p…
Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems
Muhammad Falensi Azmi, Ikhlasul Akmal Hanif, Vallerie Alexandra Putra +3
Symbolic benchmarks have emerged as a key approach to assess model robustness under minor modifications to STEM-related questions. However, existing symbolic benchmarks mostly rema…
Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages
Saeed Almheiri, Bilal Elbouardi, Salsabila Zahirah Pranida +16
Idiomatic expressions pose a major challenge for multilingual NLP because their meanings shift between figurative and literal usage, often requiring context for accurate interpreta…
IndoBias: A Dual Track Culturally Grounded Benchmark for LLMs Bias Evaluation in Indonesian Languages
Ikhlasul Akmal Hanif, Muhammad Falensi Azmi, Filbert Aurelian Tjiaranata +2
Despite being home to more than 1300 ethnic groups and 700 indigenous languages, bias in Large Language Models has not been fully studied in Indonesia, thus leaving a critical gap…
Low-Resource Safety Failures Are Action Failures, Not Representation Failures
Rashad Aziz, Ikhlasul Akmal Hanif, Fajri Koto
Language models often answer harmful requests in low-resource languages (LRLs) that they refuse in high-resource languages (HRLs). Across three instruction-tuned models and 23 lang…
TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards
Mingxuan Cui, Jingpu Yang, Fengxian Ji +7
Faithful text rendering remains a persistent weakness of large text-to-image generative models, as it requires both semantic instruction following and fine-grained glyph-level stru…
Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues
Muhammad Dehan Al Kautsar, Saeed Almheiri, Momina Ahsan +13
There is a significant gap in evaluating cultural reasoning in LLMs using conversational datasets that capture culturally rich and dialectal contexts. Most Arabic benchmarks focus…
Instruction-Guided Poetry Generation in Arabic and Its Dialects
Abdelrahman Sadallah, Kareem Elozeiri, Mervat Abassy +5
Poetry has long been a central art form for Arabic speakers, serving as a powerful medium of expression and cultural identity. While modern Arabic speakers continue to value poetry…
Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning
Yanbei Jiang, Amr Keleg, Ryandito Diandaru +4
While the real world is inherently stochastic, Large Language Models (LLMs) are predominantly evaluated on single-round inference against fixed ground truths. In this work, we shif…
Grounding AI-in-Education Development in Teachers' Voices: Findings from a National Survey in Indonesia
Nurul Aisyah, Muhammad Dehan Al Kautsar, Arif Hidayat +1
Despite emerging use in Indonesian classrooms, there is limited large-scale, teacher-centred evidence on how AI is used in practice and what support teachers need, hindering the de…
Exploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation
Nurkhan Laiyk, Gerard I. Gállego, Javier Ferrando +1
Function vectors (FVs) are vector representations of tasks extracted from model activations during in-context learning. While prior work has shown that multilingual model represent…
Listen, Correct, and Feed Back: Spoken Pedagogical Feedback Generation
Junhong Liang, Yifan Lu, Ekaterina Kochmar +1
Grammatical error correction (GEC) and explanation (GEE) have made rapid progress, but real teaching scenarios also require \emph{learner-friendly pedagogical feedback} that is act…
Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling
Alaa Elsetohy, Sama Hadhoud, Haryo Akbarianto Wibowo +4
Multilingual benchmarks rarely test reasoning over culturally grounded premises: translated datasets keep English-centric scenarios, while culture-first datasets often lack control…
LLMs as Cultural Archives: Cultural Commonsense Knowledge Graph Extraction
Junior Cedric Tonga, Chen Cecilia Liu, Iryna Gurevych +1
Large language models (LLMs) encode rich cultural knowledge learned from diverse web-scale data, offering an unprecedented opportunity to model cultural commonsense at scale. Yet t…
AMIR-GRPO: Inducing Implicit Preference Signals into GRPO
Amir Hossein Yari, Fajri Koto
Reinforcement learning has become the primary paradigm for aligning large language models (LLMs) on complex reasoning tasks, with group relative policy optimization (GRPO) widely u…
Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection
Muhammad Alif Al Hakim, Alfan Farizki Wicaksono, Fajri Koto
Quantization is widely adopted to reduce the computational cost of large language models (LLMs); however, its implications for fairness and safety, particularly in dynamic quantiza…
Vision Language Models are Confused Tourists
Patrick Amadeus Irawan, Ikhlasul Akmal Hanif, Muhammad Dehan Al Kautsar +3
Although the cultural dimension has been one of the key aspects in evaluating Vision-Language Models (VLMs), their ability to remain stable across diverse cultural inputs remains l…
Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages
Amir Hossein Yari, Kalmit Kulkarni, Ahmad Raza Khan +1
While automatic metrics drive progress in Machine Translation (MT) and Text Summarization (TS), existing metrics have been developed and validated almost exclusively for English an…
Parallel Tokenizers: Rethinking Vocabulary Design in Cross-Lingual Transfer of Low-Resource Languages
Muhammad Dehan Al Kautsar, Fajri Koto
Tokenization forms the basis of multilingual language models, yet existing methods often limit cross-lingual transfer by mapping semantically equivalent words to different embeddin…
Cross-Cultural Transfer of Commonsense Reasoning in LLMs: Evidence from the Arab World
Saeed Almheiri, Rania Hossam, Mena Attia +4
Large language models (LLMs) often reflect Western-centric biases, limiting their effectiveness in diverse cultural contexts. Although some work has explored cultural alignment, th…
Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations
Patrick Amadeus Irawan, Ryandito Diandaru, Belati Jagad Bintang Syuhada +5
We introduce Entropy2Vec, a novel framework for deriving cross-lingual language representations by leveraging the entropy of monolingual language models. Unlike traditional typolog…