arXiv:2608. 14626v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved substantial progress in safety alignment, yet their safety guarantees remain significantly weaker in low-resource and multilingual settings than in high-resource languages.
By Valdini Douglace Lemofouet, Blessing Ngozi Uzor, Paula Chikaodinaka Anyanwu, Danielle Blanche Kapsa, Sukairaj Hafiz Imam, P Sam Sahil, Abigail Oppong, Tassallah Abdullahi, Clemencia Siro, Idris Abdulmumin, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad
Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. However, this assumption remains underexplored and exposes a vulnerability in low-resource languages.
arXiv:2606. 08451v1 Announce Type: cross Abstract: Safety-aligned large language models often exhibit sycophancy, which is the tendency to affirm users' opinions regardless of factual accuracy.
By Arya Shah, Himanshu Beniwal, Mayank Singh, Chaklam Silpasuwanchai
The paper introduces MMSAFE, a multi-layer framework designed to identify safety-degrading data in multilingual large language models. It shows that safety signals are distributed across multiple layers and only partially shared across languages, unlike the single-layer assumption used in monolingual settings. Experiments demonstrate that MMSAFE reduces harmful-response rates by 60% compared to random filtering and outperforms the best single-layer baseline across various models, languages, and safety benchmarks.
By Jiakun Li, Guowei Song, Sijia Li, Xingwei He, Hongzheng Chai, Yuan Yuan
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.
By Will Hawkins, Kaivalya Rawal, Jonathan Rystr{\o}m, Stratis Tsirtsis, Zihao Fu, Greta Warren, Ryan Brown, Eoin Delaney, Sandra Wachter, Brent Mittelstadt, Chris Russell
The paper introduces HausaSafeLM, a safety preference dataset for Hausa comprising 10,000 prompts (3,000 human‑corrected and 7,000 machine‑translated) across six harm categories. Using Qwen2.5‑7B‑Instruct, the authors compare supervised fine‑tuning (SFT) and SFT followed by Direct Preference Optimization (DPO) on 500 harmful and 200 benign Hausa prompts, finding that SFT improves refusal fluency and precision—especially with larger, noisier data—while DPO sharpens precision at the cost of linguistic quality. No single approach simultaneously maximizes safety, helpfulness, and fluency, and the study shows that refusal‑rate metrics alone are unreliable indicators of safety in low‑resource languages.
By Valdini Douglace Lemofouet, Blessing Ngozi Uzor, Paula Chikaodinaka Anyanwu, Danielle Blanche Kapsa, Saminu Mohammad Aliyu, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad