arXiv:2610.20102v1 Announce Type: new Abstract: We investigate two aspects of multilingual pre-training with limited data, namely how language exposure is distributed across English, Dutch, and Chine...
arXiv:2607. 02079v1 Announce Type: cross Abstract: We present HaloGuard 1.
arXiv:2608. 13695v1 Announce Type: cross Abstract: Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe for non-English-speaking users.
The study investigates how exposing large language models to Arabic translations of English benchmark tasks can hide data contamination from standard English-only detection methods. By testing four instruction-tuned models with increasing Arabic exposure, the authors find that traditional probes like TS-Guessing and Min-K%++ fail to detect contamination, yet English performance still improves. They propose a new Translation-Aware Contamination Detection (TACD) method that uses cross-lingual consistency and choice reordering to reveal contamination effects that are otherwise invisible to English-only diagnostics.
arXiv:2606. 28843v1 Announce Type: cross Abstract: Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task.
PRISM is a framework that evaluates how activation interventions transfer across precision, languages, and model scales to mitigate unsafe tool‑calling behaviors in language models. By leveraging lower‑resource settings such as quantized NF4 labels and cross‑lingual transfer, PRISM demonstrates that alignment improvements can be achieved with minimal scenarios and that these gains transfer to held‑out languages and larger models. The study shows that auxiliary supervision from compressed models and multilingual data can effectively uncover and reduce hazardous tool‑calling behaviors across different model families.
arXiv:2605.05662v2 Announce Type: replace-cross Abstract: Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Mor...
arXiv:2606. 01196v1 Announce Type: cross Abstract: Safety alignment learned in high-resource languages transfers poorly to low-resource languages.
The paper introduces the Adversarial Surface-Form Robustness Dataset (ASRD), which contains 2,100 prompts across seven surface‑form families to test large language models on non‑canonical inputs. Five open‑weight models were evaluated on 10,500 responses, and a Quad‑State Evaluation Rubric categorized each response as harmful compliance, safe response, comprehension failure, or indeterminate. Results show that emoji and invisible Unicode variations produce few comprehension failures, while leetspeak, encoded wrappers, and hybrid transformations lead to high comprehension failure rates and varied harmful compliance percentages.
arXiv:2605. 17173v2 Announce Type: replace-cross Abstract: Large language models exhibit safety degradation in non-English languages.
Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative Steering injects undesirable-trait persona vectors dur...
arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.