Author

Luis Frentzen Salim

h-index 2 View on Semantic Scholar

We have 3 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Oct 2026

No Single Tokenizer Feature Reliably Predicts Downstream Language Model Performance

Tokenization is a critical component of the language modeling pipeline, but it is poorly understood. Tokenizers can impact downstream performance, but there is currently mixed evidence about which tokenizer features predict a better language model without requiring a full training run. In this paper, we analyze approxi...

Antonio Lopardo, Luis Frentzen Salim, Shikhar Srivastava et al. · 0 citations

#natural language process... Preprint Oct 2026

Towards Robust Calibration Dataset for Domain-General Mixture of Experts Pruning

Post-training expert pruning is a promising deployment technique for Mixture-of-Experts (MoE) models. The calibration set is an integral part of the pruning process, however, its correlation with evaluation performance is largely misunderstood and unintuitive. In this work, we present an empirical study of the robustne...

Luis Frentzen Salim, Chia-Chun Wu, Nhiem Tran et al. · 0 citations

#natural language process... Preprint Aug 2026

Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It

It is shown how fact-checking, a generally desirable behavior, can interfere with belief tracking in LLMs and how suppressing this attention at decoding time recovers accuracy only partially and only in some models, calling for future work on intervention methods.

Quang Minh Nguyen, Luis Frentzen Salim · 0 citations