AI RESEARCH
Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval
arXiv CS.LG
•
ArXi:2604.23396v1 Announce Type: cross Generative retrieval (GR) ranks documents by autoregressively generating document identifiers. Because many GR methods rely on trie-constrained beam search, they are vulnerable to early pruning of relevant prefixes under finite-beam decoding. Planning Ahead in Generative Retrieval (PAG) mitigates this failure mode by using simultaneous decoding to compute a document-level look-ahead prior that guides subsequent sequential decoding. We reproduce PAG at inference time and stress-test its decoding behavior.