Maria Marina

Self-consistency improves large language models by sampling multiple reasoning paths and selecting the most frequent answer, but majority vote often fails to recover correct answers that are already present among samples. In this work, we reformulate answer selection in self-consistency as a rank...

The presence of factual hallucinations in large language model (LLM) generations drives the development of retrieval-augmented factuality evaluation tools. However, existing implementations suffer from slow inference, outdated knowledge bases, and the use of paid search and LLM APIs, which hinder...