Existing legal benchmarks cover diverse tasks, while continuous monetary remedies remain comparatively underexplored. We introduce ECtHR-NPD, to the best of our knowledge, the first benchmark for predicting non-pecuniary damage (NPD) awards at the European Court of Human Rights (ECtHR) from case information when no sta...
Yanyi Pu, Damián A. González-Salzberg, Zheng Yuan et al.· 0 citations
Fact-Ablated Evaluation (FAE) is introduced, a new evaluation framework that iteratively ablates the cited evidence to assess whether LLMs revise their predictions accordingly and highlights that strong fact-checking performance can still coexist with weak evidence dependency, while REAL encourages veracity predictions...
Xing-Yu Deng, Mingzi Cao, Nikolaos Aletras et al.· 0 citations
This paper proposes MultiHashFormer, a new framework that allows hash-based autoregression that consistently outperforms standard Transformer LMs across multiple benchmarks and shows that the model handles multilingual vocabulary expansion with a constant parameter footprint without any modifications.
This paper initializes byte embeddings directly from the subword representations of a frozen base model, applies a chunk alignment loss to project dynamically grouped byte chunks toward precomputed subword targets, and interleave lightweight part-of-speech supervision to guide boundary detection.
