arXiv:2606. 28294v1 Announce Type: new Abstract: Preference-based alignment often struggles to capture the reasoning that underlies human judgments.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
Large Language Models (LLMs) as judges across various scenarios such as assessing model responses is becoming an increasingly accepted paradigm. However, existing judgment approaches often rely on trained judgers using fixed preference data, which tend to overlook diverse user preferences and struggle to adapt to real-world human-AI dialogue scenarios.
arXiv:2603. 23841v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) are increasingly used as primary sources of information, their potential for political bias may impact their objectivity.
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.
arXiv:2606. 30116v1 Announce Type: new Abstract: Pairwise preference data is widely used for training and evaluating language models (e.
arXiv:2608. 10186v1 Announce Type: cross Abstract: LLMs are increasingly deployed in settings that require collective reasoning on complex, value-laden problems.
arXiv:2607. 16232v1 Announce Type: cross Abstract: The growing use of statistical learning algorithms to infer human preferences from high-dimensional choice data runs up against a fundamental challenge: choice alternatives typically differ in many ways simultaneously, so it is generally unclear which factors actually drove an observed decision and should be credited as preferences.