Paper of the Day — The Latent DailyOne paper explained, every day.https://thelatentdaily.com/en-usPaper of the Day: Models act more cautiously when told they are tested, and more so in Indic languageshttps://thelatentdaily.com/research/evaluation-awareness-indic-languages/https://thelatentdaily.com/research/evaluation-awareness-indic-languages/A new study of four LLMs in five Indic languages finds that telling a model it is being safety-tested raises refusals of harmful requests by 14.4 points on average.Sun, 18 Oct 2026 06:00:00 GMTPaper of the Dayai-safetyevaluationsmultilingualllmsresearchdario_admin@resolvia-crm.techPaper of the day: Direct Preference Optimization (DPO), explainedhttps://thelatentdaily.com/research/direct-preference-optimization-dpo-paper-explained/https://thelatentdaily.com/research/direct-preference-optimization-dpo-paper-explained/DPO showed language models can be aligned to human preferences without a separate reward model or reinforcement learning. How it works and why it spread so fast.Sun, 18 Oct 2026 02:54:00 GMTPaper of the Dayresearchdpoalignmentrlhfdario_admin@resolvia-crm.techPaper of the day: Switch Transformers and the rise of mixture-of-expertshttps://thelatentdaily.com/research/switch-transformers-mixture-of-experts-explained/https://thelatentdaily.com/research/switch-transformers-mixture-of-experts-explained/Switch Transformers showed that routing each token to one expert lets models grow to a trillion parameters without proportional compute. How MoE works and why it matters.Sun, 18 Oct 2026 02:53:00 GMTPaper of the Dayresearchmixture-of-expertstransformersscalingdario_admin@resolvia-crm.tech