{"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/amortizing-intractable-inference-in-large","title":"Amortizing intractable inference in large language models","arxiv_id":"2310.04363","date":"2023-10-06","proceeding":null,"authors":["Edward J. Hu","Moksh Jain","Eric Elmoznino","Younesse Kaddar","Guillaume Lajoie","Yoshua Bengio","Nikolay Malkin"],"abstract":"Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits tractable querying of this knowledge to start-to-end autoregressive sampling. However, many tasks of interest -- including sequence continuation, infilling, and other forms of constrained generation -- involve sampling from intractable posterior distributions. We address this limitation by using amortized Bayesian inference to sample from these intractable posteriors. Such amortization is algorithmically achieved by fine-tuning LLMs via diversity-seeking reinforcement learning algorithms: generative flow networks (GFlowNets). We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training and reward-maximizing policy optimization. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem and demonstrate that our approach enables data-efficient adaptation of LLMs to tasks that require multi-step rationalization and tool use.","url_abs":"https://arxiv.org/abs/2310.04363v2","url_pdf":"https://arxiv.org/pdf/2310.04363v2.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":"amortizing-intractable-inference-in-large","repo_url":"https://github.com/GFNOrg/gfn-lm-tuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.04363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04363"}},"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":"deterministic:regex_extraction","url":"https://github.com/GFNOrg/gfn-lm-tuning","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"086865dae2d16208","entry":"generate","repo":"GFNOrg/gfn-lm-tuning","repo_kind":"official","path":"infill_subj_arithmetic/utils.py","file_url":"https://github.com/GFNOrg/gfn-lm-tuning/blob/HEAD/infill_subj_arithmetic/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"086865dae2d16208"}},{"code_sha256_prefix":"2f06af6f1f67b498","entry":"get_limited_expr","repo":"GFNOrg/gfn-lm-tuning","repo_kind":"official","path":"infill_subj_arithmetic/utils.py","file_url":"https://github.com/GFNOrg/gfn-lm-tuning/blob/HEAD/infill_subj_arithmetic/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f06af6f1f67b498"}},{"code_sha256_prefix":"dbc41d99738a49aa","entry":"left_pad","repo":"GFNOrg/gfn-lm-tuning","repo_kind":"official","path":"infill_subj_arithmetic/utils.py","file_url":"https://github.com/GFNOrg/gfn-lm-tuning/blob/HEAD/infill_subj_arithmetic/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dbc41d99738a49aa"}},{"code_sha256_prefix":"5cdeebc23c433715","entry":"remove_left_pad","repo":"GFNOrg/gfn-lm-tuning","repo_kind":"official","path":"infill_subj_arithmetic/utils.py","file_url":"https://github.com/GFNOrg/gfn-lm-tuning/blob/HEAD/infill_subj_arithmetic/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cdeebc23c433715"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}