Document Type
Conference Proceeding
Publication Date
7-13-2025
Publisher
Association for Computing Machinery
Abstract
Retrieval-augmented generation (RAG) has become integral to large language models (LLMs), particularly for conversational AI systems where user questions may reference knowledge beyond the LLMs' training cutoff. However, many natural user questions lack well-defined answers, either due to limited domain knowledge or because the retrieval system returns documents that are relevant in appearance but uninformative in content. In such cases, LLMs often produce hallucinated answers without flagging them. While recent work has largely focused on questions with false premises, we study out-of-scope questions, where the retrieved document appears semantically similar to the question but lacks the necessary information to answer it. In this paper, we propose a guided hallucination-based approach ELOQ . https://github.com/zhiyuanpeng/ELOQ.git, for automatically generating a diverse set of out-of-scope questions from post-cutoff documents, followed by human verification to ensure quality. We use this dataset to evaluate several LLMs on their ability to detect out-of-scope questions and generate appropriate responses. Finally, we introduce an improved detection method that enhances the reliability of LLM-based question-answering systems in handling out-of-scope questions.
Recommended Citation
Peng, Z., Nian, J., Evfimievski, A., & Fang, Y. (2025). ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions. Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’25, 3509–3519. https://doi.org/10.1145/3726302.3730333
Comments
Open access to this article is funded by Santa Clara University Library.
This work is licensed under Creative Commons Attribution International 4.0.