HaDeMiF: Hallucination Detection and Mitigation in Large Language Models
Keywords: Large language model, knowledge hallucination, hallucination detection, model calibration, deep neural decision tree
TL;DR: This study presents a comprehensive framework, named HaDeMiF, for the detection and mitigation of hallucinations, which harnesses the extensive knowledge embedded in both the output space and the internal hidden states of LLMs.
Abstract: The phenomenon of knowledge hallucinations has raised substantial concerns about the security and reliability of deployed large language models (LLMs). Current methods for detecting hallucinations primarily depend on manually designed individual metrics, such as prediction uncertainty and consistency, and fall short in effectively calibrating model predictions, thus constraining their detection accuracy and applicability in practical applications. In response, we propose an advanced framework, termed HaDeMiF, for detecting and mitigating hallucinations in LLMs. Specifically, hallucinations within the output and semantic spaces of LLMs are comprehensively captured through two compact networks—a novel, interpretable tree model known as the Deep Dynamic Decision Tree (D3T) and a Multilayer Perceptron (MLP)—which take as input a set of prediction characteristics and the hidden states of tokens, respectively. The predictions of LLMs are subsequently calibrated using the outputs from the D3T and MLP networks, aiming to mitigate hallucinations and enhance model calibration. HaDeMiF can be applied during both the inference and fine-tuning phases of LLMs, introducing less than 2% of the parameters relative to the LLMs through the training of two small-scale networks. Extensive experiments conclusively demonstrate the effectiveness of our framework in hallucination detection and model calibration across text generation tasks with responses of varying lengths.
Primary Area: generative models
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.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
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: 1099
Loading