Properties and Challenges of LLM-Generated Explanations

arXiv:2402.10532v1 Announce Type: cross
Abstract: The self-rationalising capabilities of large language models (LLMs) have been explored in restricted settings, using task/specific data sets. However, current LLMs do not (only) rely on specifically annotated data; nonetheless, they frequently explain their outputs. The properties of the generated explanations are influenced by the pre-training corpus and by the target data used for instruction fine-tuning. As the pre-training corpus includes a large amount of human-written explanations "in the wild", we hypothesise that LLMs adopt …

abstract annotated data arxiv capabilities challenges cs.ai cs.cl cs.hc cs.lg current data data sets generated language language models large language large language models llm llms pre-training training type