Papers › End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

15 Sep 2021EMNLP 2021 11arXiv:2109.07263archive 2025-07-28

Dinesh Raghu, Shantanu Agarwal, Sachindra Joshi, Mausam

We propose a novel problem within end-to-end learning of task-oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e.g., car not starting). Such dialogs are grounded in domain-specific flowcharts, which the agent is supposed to follow during the conversation. Our task exposes novel technical challenges for neural TOD, such as grounding an utterance to the flowchart without explicit annotation, referring to additional manual pages when user asks a clarification question, and ability to follow unseen flowcharts at test time. We release a dataset (FloDial) consisting of 2,738 dialogs grounded on 12 different troubleshooting flowcharts. We also design a neural model, FloNet, which uses a retrieval-augmented generation architecture to train the dialog agent. Our experiments find that FloNet can do zero-shot transfer to unseen flowcharts, and sets a strong baseline for future research.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples: 15 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 16: 9 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 8 ran (0 with no instrument failure; 8 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

dair-iitd/flonet officialmentioned in paperpytorchSyntology: 15 samples, 8 ran (8 instrument-failed) · 7 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran · our draft was wrong
7unverified

Licence: 16 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from dair-iitd/flonet. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

dair-iitd/flonet official repository 15 samples, 8 ran (8 instrument-failed) · 7 unverified
build_input_from_segments code/flonet.py ran · our draft was wrong no licence file found · pointer only · 97671968a986554e · report fixture: signature persona:list/1/list, history:list/1/list, reply:list/1/int, tokenizer:MockTokenizer/0/?, lm_labels:bool/0/bool, with_eos:bool/0/bool, max_input_length:int/0/int, personality_length:int/0/int, history_length:int/0/int · returned dict · level recorded 2026-09-24
choose_negative_candidate code/flonet.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 8192b16e8f847796 · report fixture: signature history:list/1/str, worst_response:str/0/str · returned str · level recorded 2026-09-24
convert_to_gpt_input code/flonet.py ran · our draft was wrong no licence file found · pointer only · 6febd43532f1a86b · report fixture: signature dataset:list/1/dict, args:MockArgs/0/?, tokenizer:MockTokenizer/0/?, use_flowchart:bool/0/bool · returned list · level recorded 2026-09-24
edit_segment_lengths code/flonet.py ran · our draft was wrong no licence file found · pointer only · a52eb5c3b7679d14 · report fixture: signature sequence:list/1/list, p_len:int/0/int, h_len:int/0/int · returned list · level recorded 2026-09-24
get_ranking_info code/flonet.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f2c82bc8ed6bae17 · report fixture: signature gt_labels:list/1/int, pred_scores:Tensor/1/float · returned tuple · level recorded 2026-09-22
make_gpt_input_json code/flonet.py ran · our draft was wrong no licence file found · pointer only · b550d33f5921150e · report fixture: signature history:list/1/str, response:str/0/str, chart_responses:list/1/str, worst_response:str/0/str · returned list · level recorded 2026-09-24
process_string in 8 papers code/flonet.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 2f703bcccbbd0509 · report fixture: signature string:str/0/str · returned str · level recorded 2026-09-22
tokenize_for_gpt code/flonet.py ran · our draft was wrong no licence file found · pointer only · 8a7bdb8e5ca6691b · report fixture: signature entries:dict/0/?, tokenizer:SimpleTokenizer/0/? · returned dict · level recorded 2026-09-24
ProxyScoreBatch code/flonet.py unverified no licence file found · pointer only · 2bca424615223036 · report
dropout_entries code/flonet.py unverified no licence file found · pointer only · 6412deef8650ce73 · report
get_lm_probs code/flonet.py unverified no licence file found · pointer only · b9c243c6ffd71c57 · report
get_p_dropouts code/flonet.py unverified no licence file found · pointer only · 363567696ac6ed29 · report
tokenize in 176 papers code/flonet.py unverified no licence file found · pointer only · d475f3f7be3b7523 · report
train in 522 papers code/flonet.py unverified no licence file found · pointer only · 308e60d9f6d6475a · report
train_gpt code/flonet.py unverified no licence file found · pointer only · 33b1dafcbe23dd23 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
pad_dataset in 5 papers repository not located ran · our draft was wrong licence of this copy not recorded · 8da3872b5fd9f84c · report fixture: signature dataset:dict/0/?, padding:int/0/int · returned dict · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for FLONET (graph method: FLONET). 16 bricks; individually on a fixture: 9 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. train entry · level 0 · unverified · 308e60d9f6d6475a
  2. ProxyScoreBatch model · level 0 · unverified · 2bca424615223036
  3. convert_to_gpt_input helper · level 1 · ran · our draft was wrong · 6febd43532f1a86b
  4. dropout_entries helper · level 0 · unverified · 6412deef8650ce73
  5. get_ranking_info metric · level 1 · ran · our draft was wrong · f2c82bc8ed6bae17
  6. make_gpt_input_json helper · level 1 · ran · our draft was wrong · b550d33f5921150e
  7. tokenize_for_gpt helper · level 1 · ran · our draft was wrong · 8a7bdb8e5ca6691b
  8. train_gpt helper · level 0 · unverified · 33b1dafcbe23dd23
  9. build_input_from_segments helper · level 1 · ran · our draft was wrong · 97671968a986554e
  10. pad_dataset helper · level 1 · ran · our draft was wrong · 8da3872b5fd9f84c
  11. get_p_dropouts helper · level 0 · unverified · 363567696ac6ed29
  12. choose_negative_candidate helper · level 1 · ran · our draft was wrong · 8192b16e8f847796
  13. process_string helper · level 1 · ran · our draft was wrong · 2f703bcccbbd0509
  14. tokenize helper · level 0 · unverified · d475f3f7be3b7523
  15. get_lm_probs helper · level 0 · unverified · b9c243c6ffd71c57
  16. edit_segment_lengths helper · level 1 · ran · our draft was wrong · a52eb5c3b7679d14

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2109.07263") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Flowchart Grounded Dialog Response GenerationRetrievalRetrieval-augmented GenerationZero-Shot Flowchart Grounded Dialog Response Generation

Datasets

Introduced by this paper, per the archive.

FloDial

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections