ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding
ReTrace is introduced, a rejected-trajectory conditioning method that conditions each draft block on the rejected suffix from the previous round rather than generating it from fresh mask placeholders alone, indicating that the draft model can retain useful semantic and structural information despite local token-level errors.
Luxi Lin, Zhan-Peng Zeng, Shuang Peng et al.
· 0 citations