arXiv:2605. 01642v2 Announce Type: replace Abstract: Prevailing alignment methods target a fixed set of preferences and therefore risk forcing value lock-in as societal norms evolve over time.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2608. 14629v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and invulnerable to political bias is a critical step towards safer and more trustworthy Artificial Intelligence (AI).
arXiv:2606. 18606v1 Announce Type: cross Abstract: It is essential for large language model (LLM) technology to serve many different cultural sub-communities in a manner that is acceptable to each community.
arXiv:2608. 00175v1 Announce Type: new Abstract: Deep reinforcement learning (RL) agents achieve strong performance by optimizing scalar reward functions.
arXiv:2601. 08097v2 Announce Type: replace-cross Abstract: Reward modeling is essential for aligning large language models with human preferences, yet predominant architectures rely on a static pooling strategy to condense sequences into scalar scores.
arXiv:2606. 28294v1 Announce Type: new Abstract: Preference-based alignment often struggles to capture the reasoning that underlies human judgments.
arXiv:2606. 30339v1 Announce Type: cross Abstract: Aligning large language models (LLMs) with diverse user preferences is a critical yet challenging task.