Juraj Vladika

When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness

An extensive evaluation shows that, on classification-style benchmarks, adding NLEs to few-shot prompts often improves accuracy over few-shot prompting without explanations; among NLE sources, externally generated LLM-NLEs often provide strong downstream utility and remain competitive with human rationales where both a...