This paper introduces a novel, integrated approach AHA ( A daptive H uman-A ssisted OOD learning) to simultaneously address both OOD generalization and detection through a human-assisted framework by labeling data in the wild.

Recent advancements in Large Language Models (LLMs) have significantly improved text generation capabilities, but these systems are still known to hallucinate, and granular uncertainty estimation for long-form LLM generations remains challenging.

Table 6 provides summary statistics of domain coverage.

A recent line of work aims at specially prompting LLMs to review their own generations and generate meaningful natural language feedback, which can subsequently be used to refine them [Madaan et al.,

Code is available at https://github.com/xbyym/DLSR. If the test data does not follow the training distribution, the model could unintentionally produce nonsensical predictions, resulting in some misleading conclusions.