{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/language-models-as-semantic-indexers","title":"Language Models As Semantic Indexers","arxiv_id":"2310.07815","date":"2023-10-11","proceeding":null,"authors":["Bowen Jin","Hansi Zeng","Guoyin Wang","Xiusi Chen","Tianxin Wei","Ruirui Li","Zhengyang Wang","Zheng Li","Yang Li","Hanqing Lu","Suhang Wang","Jiawei Han","Xianfeng Tang"],"abstract":"Semantic identifier (ID) is an important concept in information retrieval that aims to preserve the semantics of objects such as documents and items inside their IDs. Previous studies typically adopt a two-stage pipeline to learn semantic IDs by first procuring embeddings using off-the-shelf text encoders and then deriving IDs based on the embeddings. However, each step introduces potential information loss, and there is usually an inherent mismatch between the distribution of embeddings within the latent space produced by text encoders and the anticipated distribution required for semantic indexing. It is non-trivial to design a method that can learn the document's semantic representations and its hierarchical structure simultaneously, given that semantic IDs are discrete and sequentially structured, and the semantic supervision is deficient. In this paper, we introduce LMIndexer, a self-supervised framework to learn semantic IDs with a generative language model. We tackle the challenge of sequential discrete ID by introducing a semantic indexer capable of generating neural sequential discrete representations with progressive training and contrastive learning. In response to the semantic supervision deficiency, we propose to train the model with a self-supervised document reconstruction objective. We show the high quality of the learned IDs and demonstrate their effectiveness on three tasks including recommendation, product search, and document retrieval on five datasets from various domains. Code is available at https://github.com/PeterGriffinJin/LMIndexer.","url_abs":"https://arxiv.org/abs/2310.07815v3","url_pdf":"https://arxiv.org/pdf/2310.07815v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"language-models-as-semantic-indexers","repo_url":"https://github.com/petergriffinjin/lmindexer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.07815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07815"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/petergriffinjin/lmindexer","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"ecc901a1548f3862","entry":"all_reduce","repo":"petergriffinjin/lmindexer","repo_kind":"official","path":"SemanticID/src/IDGen/quantizer.py","file_url":"https://github.com/petergriffinjin/lmindexer/blob/HEAD/SemanticID/src/IDGen/quantizer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ecc901a1548f3862"}},{"code_sha256_prefix":"a32209dd55b92699","entry":"mean_pooling","repo":"petergriffinjin/lmindexer","repo_kind":"official","path":"SemanticID/src/IDGen/modeling.py","file_url":"https://github.com/petergriffinjin/lmindexer/blob/HEAD/SemanticID/src/IDGen/modeling.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a32209dd55b92699"}},{"code_sha256_prefix":"bfbc7746415f3426","entry":"load_tf_weights_in_t5","repo":"petergriffinjin/lmindexer","repo_kind":"official","path":"SemanticID/src/IDGen/reconstruct_decoder.py","file_url":"https://github.com/petergriffinjin/lmindexer/blob/HEAD/SemanticID/src/IDGen/reconstruct_decoder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bfbc7746415f3426"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}