arXiv Computation and Language November 4, 2026 By Lucinda Laurent, Muhammad Dehan Al Kautsar, Alfan Farizki Wicaksono, Fajri Koto

Steering with Multilingual Lexicons for Sentiment Control in Low-Resource Languages

Read the original on arXiv Computation and Language →

The paper proposes using multilingual sentiment lexicons to steer language models for sentiment control, especially in low-resource languages. It finds that aggregated multilingual lexicons outperform English-derived steering vectors for mid- and low-resource languages, while monolingual lexicons are still best for languages the model was pre-trained on. The study also explains how representational density, pre-training priors, and architectural biases affect steering effectiveness, noting that large English vectors can cause linguistic collapse in low-resource settings but this is mitigated by norm-dampening in multilingual aggregation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Oct 7

Cross-Lingual Activation Steering for Multilingual Language Models

arXiv:2601.16390v2 Announce Type: replace-cross Abstract: Large language models exhibit strong multilingual capabilities, yet significant performance gaps persist between dominant and non-dominant la...

By Rhitabrat Pokharel, Ameeta Agrawal, Tanay Nagar

llms benchmarks safety

arXiv Computation and Language

Sep 22

Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation

arXiv:2606.18389v2 Announce Type: replace Abstract: Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated dat...

By Jan Cegin, Daniil Gurgurov, Yusser Al Ghussin, Simon Ostermann

llms fine-tuning

arXiv AI

Sep 3

CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations

CroCo introduces cross‑lingual contrastive preference tuning on self‑generations, extending prior English‑only methods to 14 high‑ and low‑resource languages. A reward model trained solely on English preferences, applied to a multilingual base, yields effective within‑language rankings and improves performance in both monolingual and multilingual settings without catastrophic forgetting. The approach requires on‑policy data; off‑policy responses and online preference optimization offer limited gains, yet on structured tasks CroCo matches or surpasses the base model in most languages, and on open‑ended generation it wins 28/30 judge evaluations across 15 languages.

By Mike Zhang, Ali Basirat, Desmond Elliott

llms reinforcement-learning fine-tuning

arXiv Computation and Language

Aug 27

Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation

The paper investigates how to fairly compare language models across languages, noting that current evaluation methods vary widely and lack empirical validation. By training controlled monolingual models on parallel data and testing multilingual LLMs, the authors find that many normalized metrics suffer from biases due to tokenization, encoding, and orthographic differences. Instead, they recommend using sentence‑level negative log‑likelihood over semantically equivalent sequences for more reliable cross‑lingual comparisons.

By Xiulin Yang, Ethan Gotlieb Wilcox, Catherine Arnett

llms nlp

arXiv Machine Learning

Jul 28

No Optimal Language Set Exists for Multilingual Instruction Tuning: Insights from a Linguistically-Informed Study

arXiv:2410. 07809v2 Announce Type: replace-cross Abstract: Multilingual instruction tuning (MIT) is challenged by the curse of multilinguality, data scarcity, and high computational cost.

By G\"urkan Soykan, G\"ozde G\"ul \c{S}ahin

fine-tuning benchmarks

arXiv Machine Learning

Jul 7

TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior

arXiv:2512. 20757v2 Announce Type: replace-cross Abstract: Tokenizers provide the fundamental basis through which text is represented and processed by language models (LMs).

By G\"ul Sena Alt{\i}nta\c{s}, Malikeh Ehghaghi, Brian Lester, Fengyuan Liu, Wanru Zhao, Marco Ciccone, Colin Raffel

llms nlp benchmarks