2 papers
cs.CL2026
XQDT: eXplainable and Quantitative Data-Text Alignment Metric with Feedback Signals
Kun Efimov-Zhang, Yifei Song, Claire Gardent
Evaluating data-text alignment remains challenging: existing metrics often provide limited explanations for the scores, while prompt-based LLM-as-Judge methods can be expensive and…
cs.CL2026
Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data
Yifei Song, Kun Efimov-Zhang, Claire Gardent
Structured data exists in many forms (tables, knowledge graphs, charts, and time series), and converting it into text may involve different generation tasks. However, most prior wo…