Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
This addresses the issue of unreliable outputs in LLMs for users needing accurate text generation, offering a scalable solution, though it is incremental as it builds on existing decoding-based approaches.
The paper tackles the problem of hallucinations in Large Language Models by introducing Token-Guard, a token-level self-checking decoding method that reduces hallucinations and improves generation accuracy, as demonstrated on HALU datasets.
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.