{"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/predictive-querying-for-autoregressive-neural","title":"Predictive Querying for Autoregressive Neural Sequence Models","arxiv_id":"2210.06464","date":"2022-10-12","proceeding":null,"authors":["Alex Boyd","Sam Showalter","Stephan Mandt","Padhraic Smyth"],"abstract":"In reasoning about sequential events it is natural to pose probabilistic queries such as \"when will event A occur next\" or \"what is the probability of A occurring before B\", with applications in areas such as user modeling, medicine, and finance. However, with machine learning shifting towards neural autoregressive models such as RNNs and transformers, probabilistic querying has been largely restricted to simple cases such as next-event prediction. This is in part due to the fact that future querying involves marginalization over large path spaces, which is not straightforward to do efficiently in such models. In this paper we introduce a general typology for predictive queries in neural autoregressive sequence models and show that such queries can be systematically represented by sets of elementary building blocks. We leverage this typology to develop new query estimation methods based on beam search, importance sampling, and hybrids. Across four large-scale sequence datasets from different application domains, as well as for the GPT-2 language model, we demonstrate the ability to make query answering tractable for arbitrary queries in exponentially-large predictive path-spaces, and find clear differences in cost-accuracy tradeoffs between search and sampling methods.","url_abs":"https://arxiv.org/abs/2210.06464v3","url_pdf":"https://arxiv.org/pdf/2210.06464v3.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":"predictive-querying-for-autoregressive-neural","repo_url":"https://github.com/ajboyd2/prob_seq_queries","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.06464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06464"}},"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/ajboyd2/prob_seq_queries","reach":null}],"summary":{"ran":2,"ran_fixture":1,"ran_draft_wrong":4,"unverified":6},"by_repo_kind":{"official":{"samples":13,"ran":7,"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":"01f54e99a9a60e27","entry":"BSNode","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.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":"01f54e99a9a60e27"}},{"code_sha256_prefix":"84afed32bac6237d","entry":"BeamSearchSampleTree","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.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":"84afed32bac6237d"}},{"code_sha256_prefix":"2788500c55cb2165","entry":"_hidden_state_select","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2788500c55cb2165"}},{"code_sha256_prefix":"953f276962847553","entry":"_tup_cpu","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"953f276962847553"}},{"code_sha256_prefix":"5bd55c74b63a005b","entry":"_tup_cpu_gpt2","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5bd55c74b63a005b"}},{"code_sha256_prefix":"b0160851016bd79c","entry":"min_variance_top_k","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0160851016bd79c"}},{"code_sha256_prefix":"d111355f8bf308f3","entry":"top_k_top_p_filtering","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d111355f8bf308f3"}},{"code_sha256_prefix":"485281e3d11416fa","entry":"beam_search_is_hybrid","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.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":"485281e3d11416fa"}},{"code_sha256_prefix":"9e8a897fff3a55d9","entry":"beam_search_lower_bound","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.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":"9e8a897fff3a55d9"}},{"code_sha256_prefix":"4e56934b09a04cad","entry":"get_optimizer","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"scripts/train/amazon.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/scripts/train/amazon.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":"4e56934b09a04cad"}},{"code_sha256_prefix":"d5586c4a77b49699","entry":"train","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"scripts/train/amazon.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/scripts/train/amazon.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":"d5586c4a77b49699"}},{"code_sha256_prefix":"81646133d69707bb","entry":"tree_is_estimate_attn","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.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":"81646133d69707bb"}},{"code_sha256_prefix":"80a1ab04938e54b2","entry":"tree_is_estimate_rnn","repo":"ajboyd2/prob_seq_queries","repo_kind":"official","path":"seq_queries/sample.py","file_url":"https://github.com/ajboyd2/prob_seq_queries/blob/HEAD/seq_queries/sample.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":"80a1ab04938e54b2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}