LLM Detoxification via Transition-Aware Reward-Guided Representation Sampling
Read the original on arXiv AI →The paper introduces Transition-Aware Reward-Guided Representation Sampling (TARGRS), a test-time detoxification framework for large language models that learns reward guidance over toxicity transitions in latent representation space. TARGRS constructs trajectories from non‑toxic to toxic states, uses toxicity scores along these paths to train a token‑level reward model, and then guides coarse‑to‑fine sampling in the opposite direction to produce detoxified outputs with minimal perturbation. Experiments on ten LLMs and three LVLMs show that TARGRS consistently outperforms existing baselines, reducing toxicity by up to 69.38% on RealToxicityPrompts and up to 64.23% on LVLMs while maintaining near‑original speed and core capabilities.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.