collaborators

7 papers

cs.CL2026

Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models

Muhammad Faishal Adly Nelwan, Alfan Farizki Wicaksono

Activation steering edits the behaviour of a frozen language model by adding a learned vector to its residual stream, and current practice fixes the injection layers globally per t…

cs.CL2026

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…

cs.CL2026

Sparse Autoencoders Can Capture Language-Specific Concepts Across Diverse Languages

Lyzander Marciano Andrylie, Inaya Rahmanisa, Mahardika Krisna Ihsani +3

Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies…

cs.CL2025

Unveiling the Influence of Amplifying Language-Specific Neurons

Inaya Rahmanisa, Lyzander Marciano Andrylie, Mahardika Krisna Ihsani +3

Language-specific neurons in LLMs that strongly correlate with individual languages have been shown to influence model behavior by deactivating them. However, their role in amplifi…

cs.CL2025

IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages

Muhammad Falensi Azmi, Muhammad Dehan Al Kautsar, Alfan Farizki Wicaksono +1

Although region-specific large language models (LLMs) are increasingly developed, their safety remains underexplored, particularly in culturally diverse settings like Indonesia, wh…

cs.CL2025

Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation

Naila Shafirni Hidayat, Muhammad Dehan Al Kautsar, Alfan Farizki Wicaksono +1

The performance of large language models (LLMs) continues to improve, as reflected in rising scores on standard benchmarks. However, the lack of transparency around training data r…