{"ID":2862239,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.01171","arxiv_id":"2510.01171","title":"Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity","abstract":"Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this effect to algorithmic limitations, we identify a fundamental, pervasive data-level driver: typicality bias in preference data, whereby annotators systematically favor familiar text as a result of well-established findings in cognitive psychology. We formalize this bias theoretically, verify it on preference datasets empirically, and show that it plays a central role in mode collapse. Motivated by this analysis, we introduce Verbalized Sampling, a simple, training-free prompting strategy to circumvent mode collapse. VS prompts the model to verbalize a probability distribution over a set of responses (e.g., \"Generate 5 jokes about coffee and their corresponding probabilities\"). Comprehensive experiments show that VS significantly improves performance across creative writing (poems, stories, jokes), dialogue simulation, open-ended QA, and synthetic data generation, without sacrificing factual accuracy and safety. For instance, in creative writing, VS increases diversity by 1.6-2.1x over direct prompting. We further observe an emergent trend that more capable models benefit more from VS. In sum, our work provides a new data-centric perspective on mode collapse and a practical inference-time remedy that helps unlock pre-trained generative diversity.","short_abstract":"Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this effect to algorithmic limitations, we identify a fundamental, pervasive data-level driver: typicality bias in preference data, whereby annotators systematically favor familiar text...","url_abs":"https://arxiv.org/abs/2510.01171","url_pdf":"https://arxiv.org/pdf/2510.01171v3","authors":"[\"Jiayi Zhang\",\"Simon Yu\",\"Derek Chong\",\"Anthony Sicilia\",\"Michael R. Tomz\",\"Christopher D. Manning\",\"Weiyan Shi\"]","published":"2025-10-01T17:55:37Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}