Pith. sign in

REVIEW 4 cited by

Multiview Identifiers Enhanced Generative Retrieval

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.16675 v1 pith:TZDVDL54 submitted 2023-05-26 cs.CL cs.AIcs.IRcs.LG

Yongqi Li , Nan Yang , Liang Wang , Furu Wei , Wenjie Li This is my paper · ORCID
classification cs.CLcs.AIcs.IRcs.LG
keywords identifiersidentifierretrievalgenerativepassagepassagescontentmultiview
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Instead of simply matching a query to pre-existing passages, generative retrieval generates identifier strings of passages as the retrieval target. At a cost, the identifier must be distinctive enough to represent a passage. Current approaches use either a numeric ID or a text piece (such as a title or substrings) as the identifier. However, these identifiers cannot cover a passage's content well. As such, we are motivated to propose a new type of identifier, synthetic identifiers, that are generated based on the content of a passage and could integrate contextualized information that text pieces lack. Furthermore, we simultaneously consider multiview identifiers, including synthetic identifiers, titles, and substrings. These views of identifiers complement each other and facilitate the holistic ranking of passages from multiple perspectives. We conduct a series of experiments on three public datasets, and the results indicate that our proposed approach performs the best in generative retrieval, demonstrating its effectiveness and robustness.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Cold-Starts in Generative Recommendation: A Reproducibility Study

    cs.IR 2026-03 conditional novelty 6.0 of 10

    Under unified cold-start protocols, generative recommenders fail most on unseen items; identifier design, not model scale or reinforcement learning, drives cold-start generalization.

  2. MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora

    cs.IR 2025-07 conditional novelty 6.0 of 10

    A rehearsal-free generative retriever that expands mixture-of-LoRA experts only when router energy scores flag out-of-distribution tokens, achieving sublinear parameter growth over dynamic corpora.

  3. Replication and Exploration of Generative Retrieval over Dynamic Corpora

    cs.IR 2025-04 conditional novelty 6.0 of 10

    Generative retrieval with text-based docids (n-grams, titles, URLs) generalizes to newly added documents far better than numeric docids, and a constrained multi-docid numeric design recovers much of the gap on NQ.

  4. SemCORE: A Semantic-Enhanced Generative Cross-Modal Retrieval Framework with MLLMs

    cs.IR 2025-04 conditional novelty 5.0 of 10

    SemCORE improves generative cross-modal retrieval by replacing numeric image identifiers with natural-language keywords and adding an MLLM-based semantic verification reranking stage.

Pith tools