2 papers
cs.CL2025
SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone
Nishant Subramani, Alfredo Gomez, Mona Diab
Modern language models are evaluated on large benchmarks, which are difficult to make sense of, especially for model selection. Looking at the raw evaluation numbers themselves usi…
cs.CL2025
LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization
Jiarui Liu, Jivitesh Jain, Mona Diab +1
Although large language models (LLMs) have tremendous utility, trustworthiness is still a chief concern: models often generate incorrect information with high confidence. While con…