Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings
Christopher Schröder, Christopher Schröder, Lukas Gienapp +3
We identify a previously overlooked failure mode of ALiBi positional encoding: its linear bias scaling underflows floating-point precision, which zeroes out a large fraction of att…
cs.CL2025
The German Commons - 154 Billion Tokens of Openly Licensed Text for German Language Models
Lukas Gienapp, Christopher Schröder, Stefan Schweter +5
Large language model development relies on large-scale training corpora, yet most contain data of unclear licensing status, limiting the development of truly open models. This prob…