6 papers
Asymptotic Behavior of Transformers
Katy Blumer, Da-Cheng Juan, Jon Kleinberg +3
In this paper we study the behavior of transformer networks generating text over long periods of time. We show that even a three-token, single-layer attention-only transformer can…
Rubric-as-Experts: Case-Specific MQM Rubrics for Translation Error Span Detection
Weilu Xu, Yunzhi Shen, Xinye Wang +2
Large language models (LLMs) have shown potential for reference-free span-level translation quality estimation (QE), yet existing approaches based on Multidimensional Quality Metri…
Scale Determines Whether Language Models Organize Representation Geometry for Prediction
Weilun Xu
In language models, what a representation encodes is determined by the geometry of its representation space: distances, not activations, carry meaning. Existing tools characterize…
Unlocking Fine-Grained Translation Quality Estimation in LRMs through Mutually Boosting Implicit and Explicit Reasoning
Renfei Dang, Xinye Wang, Zhejian Lai +5
Large Reasoning Models (LRMs) still struggle with fine-grained translation quality estimation (QE), even with long reasoning chains. We argue that LRMs already possess strong multi…
Diachronic Modeling of Tonal Coherence on the Tonnetz Across Classical and Popular Repertoires
Weilun Xu, Edward Hall, Martin Rohrmeier
How do different musical traditions achieve tonal coherence? Most computational measures to date have analysed tonal coherence in terms of a single dimension, whereas a multi-dimen…
Probing Ethical Framework Representations in Large Language Models: Structure, Entanglement, and Methodological Challenges
Weilun Xu, Alexander Rusnak, Frederic Kaplan
When large language models make ethical judgments, do their internal representations distinguish between normative frameworks, or collapse ethics into a single acceptability dimens…