FacLens: Transferable Probe for Foreseeing Non-Factuality in Large Language Models
Keywords: Large language models, hidden question representation, non-factuality predictor, transferability
Abstract: Despite advancements in large language models (LLMs), non-factual responses remain prevalent. Unlike extensive studies on post-hoc detection of such responses, this work studies non-factuality prediction (NFP), aiming to predict whether an LLM will generate a non-factual response to a question before the generation process. Previous efforts on NFP have demonstrated LLMs' awareness of their internal knowledge, but they still face challenges in efficiency and transferability. In this work, we propose a lightweight NFP model named Factuality Lens (FacLens), which effectively probes hidden representations of questions for the NFP task. Besides, we discover that hidden question representations sourced from different LLMs exhibit similar NFP patterns, which enables the transferability of FacLens across LLMs to reduce development costs. Extensive experiments highlight FacLens’s superiority in both effectiveness and efficiency.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 9638
Loading