APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation

ArXi:2605.09492v1 Announce Type: cross Large language models (LLMs) often suffer from hallucinations due to error accumulation in autoregressive decoding, where suboptimal early token choices misguide subsequent generation. Although multi-path decoding can improve robustness by exploring alternative trajectories, existing methods lack principled strategies for determining when to branch and how to regulate inter-path interactions.