{"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/bottleneck-minimal-indexing-for-generative","title":"Bottleneck-Minimal Indexing for Generative Document Retrieval","arxiv_id":"2405.10974","date":"2024-05-12","proceeding":null,"authors":["Xin Du","Lixin Xiu","Kumiko Tanaka-Ishii"],"abstract":"We apply an information-theoretic perspective to reconsider generative document retrieval (GDR), in which a document $x \\in X$ is indexed by $t \\in T$, and a neural autoregressive model is trained to map queries $Q$ to $T$. GDR can be considered to involve information transmission from documents $X$ to queries $Q$, with the requirement to transmit more bits via the indexes $T$. By applying Shannon's rate-distortion theory, the optimality of indexing can be analyzed in terms of the mutual information, and the design of the indexes $T$ can then be regarded as a {\\em bottleneck} in GDR. After reformulating GDR from this perspective, we empirically quantify the bottleneck underlying GDR. Finally, using the NQ320K and MARCO datasets, we evaluate our proposed bottleneck-minimal indexing method in comparison with various previous indexing methods, and we show that it outperforms those methods.","url_abs":"https://arxiv.org/abs/2405.10974v2","url_pdf":"https://arxiv.org/pdf/2405.10974v2.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":"bottleneck-minimal-indexing-for-generative","repo_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.10974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10974"}},"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/kduxin/Bottleneck-Minimal-Indexing","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":11,"ran":9,"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":0,"samples":[{"code_sha256_prefix":"cf90b576db7b4cc6","entry":"chunker","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"BMIndexing/bert_embedding.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/BMIndexing/bert_embedding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf90b576db7b4cc6"}},{"code_sha256_prefix":"5d140ce18f0b48ed","entry":"clean_text","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"NCIRetriever/model.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d140ce18f0b48ed"}},{"code_sha256_prefix":"083639169ab3b8f0","entry":"convert_tf_weight_name_to_pt_weight_name","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"NCIRetriever/nci_transformers/modeling_tf_pytorch_utils.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/nci_transformers/modeling_tf_pytorch_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"083639169ab3b8f0"}},{"code_sha256_prefix":"ea31caa9a38cca23","entry":"detach_dict","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"NCIRetriever/model.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea31caa9a38cca23"}},{"code_sha256_prefix":"6d254a1b39c650ff","entry":"find_pruneable_heads_and_indices","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"NCIRetriever/nci_transformers/modeling_utils.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/nci_transformers/modeling_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d254a1b39c650ff"}},{"code_sha256_prefix":"8ccd1445bde3ebe0","entry":"intarray_to_string","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"NCIRetriever/io.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/io.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ccd1445bde3ebe0"}},{"code_sha256_prefix":"2ecf9d52d1413149","entry":"prune_conv1d_layer","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"NCIRetriever/nci_transformers/modeling_utils.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/nci_transformers/modeling_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ecf9d52d1413149"}},{"code_sha256_prefix":"b3504e72ce1153fe","entry":"prune_linear_layer","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"NCIRetriever/nci_transformers/modeling_utils.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/nci_transformers/modeling_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3504e72ce1153fe"}},{"code_sha256_prefix":"c0cf1196424d4f71","entry":"softmax","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"NCIRetriever/model.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/NCIRetriever/model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0cf1196424d4f71"}},{"code_sha256_prefix":"9cacde1e22f5c412","entry":"encode","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"BMIndexing/bert_embedding.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/BMIndexing/bert_embedding.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9cacde1e22f5c412"}},{"code_sha256_prefix":"54fe86d917d7ff48","entry":"gen_query","repo":"kduxin/Bottleneck-Minimal-Indexing","repo_kind":"official","path":"BMIndexing/genq.py","file_url":"https://github.com/kduxin/Bottleneck-Minimal-Indexing/blob/HEAD/BMIndexing/genq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54fe86d917d7ff48"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}