arXiv:2512. 15765v3 Announce Type: replace Abstract: Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multiple sources.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2505. 10892v2 Announce Type: replace Abstract: Post-training LLMs with RLHF and preference optimization methods (e.
arXiv:2509. 23982v2 Announce Type: replace-cross Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences.
arXiv:2606. 30339v1 Announce Type: cross Abstract: Aligning large language models (LLMs) with diverse user preferences is a critical yet challenging task.
arXiv:2606. 10217v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties.
arXiv:2509. 23102v4 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models with human preferences.
arXiv:2603. 03672v2 Announce Type: replace Abstract: The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space.