arXiv:2606. 30116v1 Announce Type: new Abstract: Pairwise preference data is widely used for training and evaluating language models (e.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2606. 28294v1 Announce Type: new Abstract: Preference-based alignment often struggles to capture the reasoning that underlies human judgments.
arXiv:2607. 08731v1 Announce Type: cross Abstract: A national language model offers a linguistic community its own instrument for measuring what its citizens say and value.
A national language model offers a linguistic community its own instrument for measuring what its citizens say and value. Portugal's AMALIA, a publicly funded 9B-parameter model for European Portuguese, appears competitive on agreement alone: asked to code the moral foundation of authority, it agrees with trained human coders to within six F1 points of open models eight to thirteen times its size.
arXiv:2606. 15420v1 Announce Type: cross Abstract: A constitution tells a language model what to value, but little tells us whether it does.
arXiv:2601. 14295v4 Announce Type: replace Abstract: Large language models increasingly function as artificial reasoners: they evaluate arguments, assign credibility, and express confidence.
arXiv:2607. 25136v1 Announce Type: new Abstract: Research on preference optimization often varies the training objective while holding the data fixed.