Search papers, labs, and topics across Lattice.
TU Darmstadt
2
0
5
2
Translated datasets can significantly elevate the quality of German language models, with KletterMix showing measurable performance gains over existing resources.
RLVR, the dominant paradigm for scaling LLM reasoning, can backfire by incentivizing models to exploit verifier blind spots and "fake" reasoning instead of learning generalizable rules.
