{"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":"/paper/eva2-0-investigating-open-domain-chinese","title":"EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training","arxiv_id":"2203.09313","date":"2022-03-17","proceeding":null,"authors":["Yuxian Gu","Jiaxin Wen","Hao Sun","Yi Song","Pei Ke","Chujie Zheng","Zheng Zhang","Jianzhu Yao","Lei Liu","Xiaoyan Zhu","Minlie Huang"],"abstract":"Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems. However, previous works mainly focus on showing and evaluating the conversational performance of the released dialogue model, ignoring the discussion of some key factors towards a powerful human-like chatbot, especially in Chinese scenarios. In this paper, we conduct extensive experiments to investigate these under-explored factors, including data quality control, model architecture designs, training approaches, and decoding strategies. We propose EVA2.0, a large-scale pre-trained open-domain Chinese dialogue model with 2.8 billion parameters, and will make our models and codes publicly available. Automatic and human evaluations show that EVA2.0 significantly outperforms other open-source counterparts. We also discuss the limitations of this work by presenting some failure cases and pose some future research directions on large-scale Chinese open-domain dialogue systems.","url_abs":"https://arxiv.org/abs/2203.09313v3","url_pdf":"https://arxiv.org/pdf/2203.09313v3.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":"eva2-0-investigating-open-domain-chinese","repo_url":"https://github.com/thu-coai/EVA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"eva2-0-investigating-open-domain-chinese","repo_url":"https://github.com/MindSpore-scientific/code-6/tree/main/open-domain-dialogue","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"chatbot","task_name":"Chatbot"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.09313","atlas_url":"https://app.syntology.ai/?focus=2203.09313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09313"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.09313"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.09313"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.09313\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2203.09313"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2203.09313\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2203.09313"},"call":"get_concepts_for_paper(arxiv_id=\"2203.09313\")"}],"by_repo":[{"repo":"thu-coai/EVA","kind":"official","samples":12,"ran":12,"instrument":1,"unverified":0},{"repo":"MindSpore-scientific/code-6","kind":"listed","samples":1,"ran":1,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2203.09313.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2203.09313.svg"},"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/thu-coai/EVA","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-6/tree/main/open-domain-dialogue","reach":null}],"summary":{"ran":12,"ran_draft_wrong":1},"n_samples":13,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":12,"ran":12,"n_ran_checked":11,"n_instrument":1,"repositories":1},"listed":{"samples":1,"ran":1,"n_ran_checked":1,"n_instrument":0,"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":2,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":2,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":13,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"e8c5531fe7efa529","code_sha256_prefix":"e8c5531fe7efa529","entry":"add_fp16_config_args","repo":"thu-coai/EVA","repo_kind":"official","path":"src/arguments.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/arguments.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"parser:ArgumentParser/0/?","fixture_out_type":"ArgumentParser","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e8c5531fe7efa529"}},{"code_sha256":"41b2dbbded142fc1","code_sha256_prefix":"41b2dbbded142fc1","entry":"add_model_config_args","repo":"thu-coai/EVA","repo_kind":"official","path":"src/arguments.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/arguments.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"parser:ArgumentParser/0/?","fixture_out_type":"ArgumentParser","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":"/code/add-model-config-args","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"41b2dbbded142fc1"}},{"code_sha256":"81695f53d395ab64","code_sha256_prefix":"81695f53d395ab64","entry":"add_training_args","repo":"thu-coai/EVA","repo_kind":"official","path":"src/arguments.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/arguments.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"parser:ArgumentParser/0/?","fixture_out_type":"ArgumentParser","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":"/code/add-training-args","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"81695f53d395ab64"}},{"code_sha256":"114cf78c86343fa4","code_sha256_prefix":"114cf78c86343fa4","entry":"calc_banned_antonym_words_ids","repo":"thu-coai/EVA","repo_kind":"official","path":"src/generation_utils.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/generation_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"input_tokens:Tensor/2/int, tokenizer:MockTokenizer/0/?, antonym_dict:dict/0/?","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"114cf78c86343fa4"}},{"code_sha256":"72d3cab82bc65d33","code_sha256_prefix":"72d3cab82bc65d33","entry":"calculate_gain","repo":"MindSpore-scientific/code-6","repo_kind":"listed","path":"neural-audio-synthesis-wavenet/WaveNetEncoder.py","file_url":"https://github.com/MindSpore-scientific/code-6/blob/HEAD/neural-audio-synthesis-wavenet/WaveNetEncoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"nonlinearity:str/0/str, param:NoneType/0/?","fixture_out_type":"float","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":"/code/calculate-gain","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"72d3cab82bc65d33"}},{"code_sha256":"af65f3906cd81298","code_sha256_prefix":"af65f3906cd81298","entry":"construct_antonym_dict","repo":"thu-coai/EVA","repo_kind":"official","path":"src/generation_utils.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/generation_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"args:Args/0/?","fixture_out_type":"defaultdict","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"af65f3906cd81298"}},{"code_sha256":"1923fc05163d207d","code_sha256_prefix":"1923fc05163d207d","entry":"convert_to_unicode","repo":"thu-coai/EVA","repo_kind":"official","path":"src/tokenization_eva.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/tokenization_eva.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"text:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"1923fc05163d207d"},"code_page":"/code/convert-to-unicode","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from huawei-noah/Pretrained-Language-Model, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"code_sha256":"824e9c994c649f1d","code_sha256_prefix":"824e9c994c649f1d","entry":"get_attn_masks","repo":"thu-coai/EVA","repo_kind":"official","path":"src/eva_interactive.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/eva_interactive.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"args:Args/0/?, tokenizer:Tokenizer/0/?, contexts:Tensor/2/int, targets:Tensor/2/int","fixture_out_type":"dict","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"824e9c994c649f1d"}},{"code_sha256":"448c7945683d52e4","code_sha256_prefix":"448c7945683d52e4","entry":"init_method_normal","repo":"thu-coai/EVA","repo_kind":"official","path":"src/model/eva_modeling.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/model/eva_modeling.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"std:float/0/float","fixture_out_type":"function","level_recorded_at":"2026-09-25T12:08:31.494501+00:00","code_page":"/code/init-method-normal","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"448c7945683d52e4"}},{"code_sha256":"deb4d1793cf3ba73","code_sha256_prefix":"deb4d1793cf3ba73","entry":"load_vocab","repo":"thu-coai/EVA","repo_kind":"official","path":"src/tokenization_eva.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/tokenization_eva.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"vocab_file:str/0/str","fixture_out_type":"OrderedDict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/load-vocab","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from blcuicall/CCL2022-CLTC, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"deb4d1793cf3ba73"}},{"code_sha256":"88a41f3211226c0e","code_sha256_prefix":"88a41f3211226c0e","entry":"merge","repo":"thu-coai/EVA","repo_kind":"official","path":"src/change_mp.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/change_mp.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model_parts:list/1/dict","fixture_out_type":"dict","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":"/code/merge","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"88a41f3211226c0e"}},{"code_sha256":"1e4734d93a0d4a9e","code_sha256_prefix":"1e4734d93a0d4a9e","entry":"my_lcs","repo":"thu-coai/EVA","repo_kind":"official","path":"src/generation_metrics.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/generation_metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"string:list/1/str, sub:list/1/str","fixture_out_type":"int","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":"/code/my-lcs","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1e4734d93a0d4a9e"}},{"code_sha256":"61d59af2776f4b6e","code_sha256_prefix":"61d59af2776f4b6e","entry":"split","repo":"thu-coai/EVA","repo_kind":"official","path":"src/change_mp.py","file_url":"https://github.com/thu-coai/EVA/blob/HEAD/src/change_mp.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:dict/0/?, mp:int/0/int","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":"/code/split","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"61d59af2776f4b6e"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4ce01757725d1609caf759f1b15b1906df9b7631d1baa4d49efc62c892670b3d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}