Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance
Shailja Thakur, Sungeun An, Chad DeLuca +1
A benchmark score comes from a single phrasing of each problem. That single phrasing is treated as if it stood for the whole space of ways the same problem could be asked, but it d…
cs.CL2026
STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs
Sungeun An, Swanand Ravindra Kadhe, Shailja Thakur +2
Benchmarks are often used as a standard to understand LLM capabilities in different domains. However, aggregate benchmark scores provide limited insight into compositional skill ga…
cs.CL2025
Backprompting: Leveraging Synthetic Production Data for Health Advice Guardrails
Kellen Tan Cheng, Anna Lisa Gentile, Chad DeLuca +1
The pervasiveness of large language models (LLMs) in enterprise settings has also brought forth a significant amount of risks associated with their usage. Guardrails technologies a…