{"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/on-compositionality-and-improved-training-of","title":"DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models","arxiv_id":"2306.11825","date":"2023-06-20","proceeding":null,"authors":["Sidi Lu","Wenbo Zhao","Chenyang Tao","Arpit Gupta","Shanchan Wu","Tagyoung Chung","Nanyun Peng"],"abstract":"NeurAlly-Decomposed Oracle (NADO) is a powerful approach for controllable generation with large language models. It is designed to avoid catastrophic forgetting while achieving guaranteed convergence to an entropy-maximized closed-form optimal solution with reasonable modeling capacity. Despite the success, several challenges arise when apply NADO to a wide range of scenarios. Vanilla NADO suffers from gradient vanishing for low-probability control signals and is highly reliant on a regularization to satisfy the stochastic version of Bellman equation. In addition, the vanilla implementation of NADO introduces a few additional transformer layers, suffering from a limited capacity especially compared to other finetune-based model adaptation methods like LoRA. In this paper, we propose a improved version of the NADO algorithm, namely DiNADO (norm-Disentangled NeurAlly-Decomposed Oracles), which improves the performance of the NADO algorithm through disentangling the step-wise global norm over the approximated oracle $R$-value for all potential next-tokens, allowing DiNADO to be combined with finetuning methods like LoRA. We discuss in depth how DiNADO achieves better capacity, stability and flexibility with both empirical and theoretical results. Experiments on formality control in machine translation and the lexically constrained generation task CommonGen demonstrates the significance of the improvements.","url_abs":"https://arxiv.org/abs/2306.11825v2","url_pdf":"https://arxiv.org/pdf/2306.11825v2.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":"on-compositionality-and-improved-training-of","repo_url":"https://github.com/pluslabnlp/dinado","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.11825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.11825"}},"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/pluslabnlp/dinado","reach":null}],"summary":{"ran_draft_wrong":4},"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":"8ba0f8f3e23a2d69","entry":"log1mexp","repo":"pluslabnlp/dinado","repo_kind":"official","path":"modeling_nado_gpt2.py","file_url":"https://github.com/pluslabnlp/dinado/blob/HEAD/modeling_nado_gpt2.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ba0f8f3e23a2d69"}},{"code_sha256_prefix":"092cd75165a8db61","entry":"read_lines","repo":"pluslabnlp/dinado","repo_kind":"official","path":"evaluation/eval_kit/measure_scores.py","file_url":"https://github.com/pluslabnlp/dinado/blob/HEAD/evaluation/eval_kit/measure_scores.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"092cd75165a8db61"}},{"code_sha256_prefix":"09fd8ff7fa76a6fc","entry":"read_and_check_tsv","repo":"pluslabnlp/dinado","repo_kind":"official","path":"evaluation/eval_kit/measure_scores.py","file_url":"https://github.com/pluslabnlp/dinado/blob/HEAD/evaluation/eval_kit/measure_scores.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"09fd8ff7fa76a6fc"}},{"code_sha256_prefix":"c126f81476443991","entry":"read_tsv","repo":"pluslabnlp/dinado","repo_kind":"official","path":"evaluation/eval_kit/measure_scores.py","file_url":"https://github.com/pluslabnlp/dinado/blob/HEAD/evaluation/eval_kit/measure_scores.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c126f81476443991"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}