An arXiv preprint released October 14 2026 presents Manacá-1B-Instruct-2, a safety-aligned 1.72B native Brazilian-Portuguese model. The abstract-only capture details failed DPO…
arXiv preprint presents FaithAlign, a 460-item dataset with 4982 annotated phrase-level links, plus FaithAlign-Gap, to test context-aware faithfulness evaluation in…
arXiv preprint dated 2026-10-13 introduces LlMBO, a gradient-free Bayesian optimization approach for fine-tuning LLMs with under 10 parameters, positioning it as a…
A fresh arXiv preprint introduces DDRG, which goes beyond simple answer voting by spotting and correcting disagreements in the intermediate reasoning steps of large language…
arXiv preprint presents COMPASS, a diagnostic using k-NN overlap to predict compatibility of pretrained model pairs for alignment or merging, offering a low-cost filter before…
This arXiv preprint presents MultiAlloc, a framework that uses offline profiling of layer sensitivity and token importance to allocate limited quantization resources between…
A new preprint presents BASIS, a training-free Bayesian method that infers which similarity criterion from a supplied library governs LLM decisions using weak interactive…
A new arXiv preprint proposes MATCHA, which jointly learns layer correspondences and feature transformations to align activations across independently trained large language…
arXiv preprint dated 2026-10-06 introduces Q-PACE, a second-order sensitivity model using per-layer curvature coefficients to dynamically assign mixed precision during QAT…
A new arXiv preprint introduces a two-stage framework that helps compact AI models generate realistic patient dialogues for Substance Use Disorder counseling by modeling hidden…
arXiv abstract dated 2026-10-06 introduces CurveTQ, a rotation-free trellis codec for two-bit LLM weights that incorporates Hessian curvature into the Viterbi metric and adds…