Saved in:
Bibliographic Details
Main Authors: Zhu, Yifan, Rong, Huiqiang, Luo, Haoran
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.21969
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Large Language Models (LLMs) often hallucinate, generating content inconsistent with the input. Retrieval-Augmented Generation (RAG) and Reinforcement Learning with Human Feedback (RLHF) can mitigate hallucinations but require resource-intensive retrieval or large-scale fine-tuning. Decoding-based methods are lighter yet lack explicit hallucination control. To address this, we present Token-Guard, a token-level hallucination control method based on self-checking decoding. Token-Guard performs internal verification at each reasoning step to detect hallucinated tokens before they propagate. Candidate fragments are further evaluated in a latent space with explicit hallucination risk scoring, while iterative pruning and regeneration dynamically correct detected errors. Experiments on HALU datasets show Token-Guard substantially reduces hallucinations and improves generation accuracy, offering a scalable, modular solution for reliable LLM outputs. Our code is publicly available.