Pith. sign in

REVIEW 9 cited by

Autoregressive Entity 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 2010.00904 v3 pith:XZACYZ2H submitted 2020-10-02 cs.CL cs.IRcs.LGstat.ML

Nicola De Cao , Gautier Izacard , Sebastian Riedel , Fabio Petroni This is my paper · ORCID
classification cs.CLcs.IRcs.LGstat.ML
keywords entityentitiesautoregressivefootprintmemorycontextdatadense
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Entities are at the center of how we represent and aggregate knowledge. For instance, Encyclopedias such as Wikipedia are structured by entities (e.g., one per Wikipedia article). The ability to retrieve such entities given a query is fundamental for knowledge-intensive tasks such as entity linking and open-domain question answering. Current approaches can be understood as classifiers among atomic labels, one for each entity. Their weight vectors are dense entity representations produced by encoding entity meta information such as their descriptions. This approach has several shortcomings: (i) context and entity affinity is mainly captured through a vector dot product, potentially missing fine-grained interactions; (ii) a large memory footprint is needed to store dense representations when considering large entity sets; (iii) an appropriately hard set of negative data has to be subsampled at training time. In this work, we propose GENRE, the first system that retrieves entities by generating their unique names, left to right, token-by-token in an autoregressive fashion. This mitigates the aforementioned technical issues since: (i) the autoregressive formulation directly captures relations between context and entity name, effectively cross encoding both; (ii) the memory footprint is greatly reduced because the parameters of our encoder-decoder architecture scale with vocabulary size, not entity count; (iii) the softmax loss is computed without subsampling negative data. We experiment with more than 20 datasets on entity disambiguation, end-to-end entity linking and document retrieval tasks, achieving new state-of-the-art or very competitive results while using a tiny fraction of the memory footprint of competing systems. Finally, we demonstrate that new entities can be added by simply specifying their names. Code and pre-trained models at https://github.com/facebookresearch/GENRE.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 200 citations worldwide. Full citation record

  1. Bridging the Structural Gap: Adapting Autoregressive Generation for Recommendation

    cs.IR 2026-07 conditional novelty 6.0 of 10

    BARGE improves generative sequential recommendation by restoring item boundaries in the encoder and suppressing hierarchical semantic drift in decoding, outperforming prior generative baselines on public and industria...

  2. Beyond Semantic IDs: Encoding Business-Value Ranking into Document Identifiers for Generative Retrieval

    cs.IR 2026-07 conditional novelty 6.0 of 10

    Encoding business-value ranks inside semantic clusters yields collision-free DocIDs that improve generative-retrieval Hitrate and deliver +1.06% GMV online.

  3. Generative Chinese Statute Retrieval

    cs.IR 2026-07 conditional novelty 6.0 of 10

    A generative retriever with multi-granularity structured statute IDs and multi-task training outperforms strong sparse, dense, and legal baselines on the STARD Chinese statute benchmark.

  4. GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models

    cs.AI 2026-06 conditional novelty 6.0 of 10

    A LoRA-tuned LLM with trie-constrained decoding improves grocery category recommendation and yields a 7.5% cart-add lift in production.

  5. MedPath: Multi-Domain Cross-Vocabulary Hierarchical Paths for Biomedical Entity Linking

    cs.CL 2025-11 conditional novelty 6.0 of 10

    MedPath combines 513k+ expert-annotated biomedical mentions into a UMLS-normalized dataset with cross-vocabulary mappings and hierarchical paths for 11 vocabularies.

  6. NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

    cs.IR 2025-09 conditional novelty 6.0 of 10

    Mid-layer LLM value vectors, projected through a contrastively trained MLP, enable zero-shot retrieval of documents by ad-hoc entity type.

  7. Pailitao-MMSearch: Building Native E-Commerce Multimodal Search Foundation

    cs.AI 2026-07 conditional novelty 5.0 of 10

    Alibaba's Pailitao-MMSearch combines discrete product codes with a continuous embedding so a vision-language model can generate and rank products end-to-end, reporting big but incompletely documented A/B gains.

  8. I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A text-first, multi-round visual feedback framework reports state-of-the-art top-1 accuracy on WikiMEL, WikiDiverse, and RichMEL.

  9. EGA-V2: An End-to-end Generative Framework for Industrial Advertising

    cs.IR 2025-05 conditional novelty 5.0 of 10

    EGA-V2 unifies ad ranking, creative selection, allocation, and payment into one generative transformer, and reports offline revenue and CTR improvements over cascaded and generative baselines on Meituan data.

Pith tools