{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/dapo","slug":"dapo","name":"DAPO","full_name":"Dialogue-Adaptive Pre-training Objective","full_name_withheld":false,"description_markdown":"**Dialogue-Adaptive Pre-training Objective (DAPO)** is a pre-training objective for dialogue adaptation, which is designed to measure qualities of dialogues from multiple important aspects, like Readability, Consistency and Fluency which have already been focused on by general LM pre-training objectives, and those also significant for assessing dialogues but ignored by general LM pre-training objectives, like Diversity and Specificity.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Dialogue-adaptive Language Model Pre-training From Quality Estimation","paper":"/paper/task-specific-objectives-of-pre-trained","first_author":"Junlong Li","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/task-specific-objectives-of-pre-trained"},"source":{"url":"https://arxiv.org/abs/2009.04984v2","title":"Dialogue-adaptive Language Model Pre-training From Quality Estimation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Dialog Adaptation","url":"/methods/category/dialog-adaptation","pwc_aliases":[]}],"n_papers_tagged":11,"archive_num_papers":11,"papers_newest_first":[{"paper":null,"slug":"memagent-reshaping-long-context-llm-with","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","date":"2025-07-03","arxiv_id":"2507.02259","n_code_links":0,"syntology":null},{"paper":null,"slug":"codev-r1-reasoning-enhanced-verilog","title":"CodeV-R1: Reasoning-Enhanced Verilog Generation","date":"2025-05-30","arxiv_id":"2505.24183","n_code_links":0,"syntology":null},{"paper":null,"slug":"cothink-token-efficient-reasoning-via","title":"CoThink: Token-Efficient Reasoning via Instruct Models Guiding Reasoning Models","date":"2025-05-28","arxiv_id":"2505.22017","n_code_links":0,"syntology":null},{"paper":"/paper/masksearch-a-universal-pre-training-framework","slug":"masksearch-a-universal-pre-training-framework","title":"MASKSEARCH: A Universal Pre-Training Framework to Enhance Agentic Search Capability","date":"2025-05-26","arxiv_id":"2505.20285","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-the-sampling-criteria-in","title":"Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective","date":"2025-05-23","arxiv_id":"2505.17652","n_code_links":0,"syntology":null},{"paper":"/paper/ktae-a-model-free-algorithm-to-key-tokens","slug":"ktae-a-model-free-algorithm-to-key-tokens","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","date":"2025-05-22","arxiv_id":"2505.16826","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["xiaolizh1/ktae"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/disco-reinforcing-large-reasoning-models-with","slug":"disco-reinforcing-large-reasoning-models-with","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","date":"2025-05-18","arxiv_id":"2505.12366","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["optimization-ai/disco"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"vapo-efficient-and-reliable-reinforcement","title":"VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks","date":"2025-04-07","arxiv_id":"2504.05118","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-multi-step-reasoning-abilities-of","title":"Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization","date":"2024-12-24","arxiv_id":"2412.18279","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-approximation-policy-optimization","title":"Dual Approximation Policy Optimization","date":"2024-10-02","arxiv_id":"2410.01249","n_code_links":0,"syntology":null},{"paper":"/paper/task-specific-objectives-of-pre-trained","slug":"task-specific-objectives-of-pre-trained","title":"Dialogue-adaptive Language Model Pre-training From Quality Estimation","date":"2020-09-10","arxiv_id":"2009.04984","n_code_links":1,"syntology":null}],"papers_shown":11,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":11,"with_a_code_link":4,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":11,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/dapo/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/dapo/papers/ran/1","json":"/method/dapo/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/mathematical-reasoning","name":"Mathematical Reasoning","papers":2},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":2},{"task":null,"name":"8k","papers":1},{"task":"/task/gsm8k","name":"GSM8K","papers":1},{"task":"/task/informativeness","name":"Informativeness","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/multi-hop-question-answering","name":"Multi-hop Question Answering","papers":1},{"task":"/task/offline-rl","name":"Offline RL","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/scheduling","name":"Scheduling","papers":1},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":1},{"task":"/task/specificity","name":"Specificity","papers":1},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":1}],"tasks_shown":16,"n_tasks":16,"usage_by_year":[{"year":"2020","papers":1},{"year":"2024","papers":2},{"year":"2025","papers":8}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/dapo"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=DAPO","read_at":"2026-10-05T00:54:28+00:00","query":"DAPO","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"DAPO","origin_arxiv_id":"2503.14476"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"2009.04984","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"mentioned_in_github"},"retrieve_with":null,"name_competition":{"verdict":"contested","may_be_wrong_sense":false,"bearers_found":4,"served":{"arxiv_id":"2503.14476","citations":2451},"leading_other_bearer":{"arxiv_id":"2512.11342","title":"DAPO: Design Structure-Aware Pass Ordering in High-Level Synthesis with Graph Contrastive and Reinforcement Learning","citations":null,"named_by":["title_prefix"],"bearer_name":"DAPO: Design Structure-Aware Pass Ordering in High-Level Synthesis with Graph Contrastive and Reinforcement Learning","ask_with":"have('2512.11342')"},"n_other_bearers_listed":3,"note":"3 other thing(s) here are also called 'DAPO', and none of them is cited more than the paper this answer is about. They are listed in `also_named` -- check `served.arxiv_id` is the paper you meant."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2503.14476","page":"/paper/dapo-an-open-source-llm-reinforcement","syntology_url":"https://syntology.ai/paper/2503.14476","in_graph_layer":false,"samples":0},"line":"about another paper, arXiv:2503.14476: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: mentioned on GitHub). About another paper: this answer is about arXiv:2503.14476, while the archive credits arXiv:2009.04984.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"66674d3339e2dc1f75701f58f1ba014551466bde42002bb43e7b0d84248669cb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}