@inproceedings{yang-etal-2026-cosched,
title = "{C}o{S}ched-Cert: Faithful Multi-Turn Scheduling Dialogue via Solver-Verified Certificates",
author = "Yang, Zida and
Zou, Minhao and
Peng, Yijie",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.24/",
pages = "310--321",
ISBN = "979-8-89176-478-1",
abstract = "Multi-turn scheduling assistants must preserve constraint edits and distinguish solver evidence from language-model interpretations. We present CoSched-Cert, a dialogue protocol combining a typed scheduling language, solver-distinguishing clarification, cost-based conflict localization, verified repair synthesis, and lexical certificate auditing. Its guarantees are conditional on the encoded problem and supplied candidate interpretations; lexical support does not establish semantic entailment. SchedNL-Bench-Cert contains 1,000 synthetic Chinese/English utterances and 350 sessions. Gold-AST replay measures internal consistency against labels generated by the same engine, while author-written protocol simulations illustrate selected design choices. Across three live-parser seeds on 52 sessions, session training and registered sibling augmentation raise conditional micro target-constraint agreement from 18.0{\%} to 83.7{\%}. The final configuration has 100{\%} coarse status agreement but only 75.0{\%} conflict-member agreement, and includes a rule informed by a test-session failure. We therefore treat these results as descriptive, not as an unbiased generalization estimate. We define a stricter joint-turn criterion and report the bounds supported by the available aggregates. The contribution is a protocol for exposing inspectable solver evidence and the remaining gap between encoded feasibility and user-intent correctness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-cosched">
<titleInfo>
<title>CoSched-Cert: Faithful Multi-Turn Scheduling Dialogue via Solver-Verified Certificates</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zida</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minhao</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yijie</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>Multi-turn scheduling assistants must preserve constraint edits and distinguish solver evidence from language-model interpretations. We present CoSched-Cert, a dialogue protocol combining a typed scheduling language, solver-distinguishing clarification, cost-based conflict localization, verified repair synthesis, and lexical certificate auditing. Its guarantees are conditional on the encoded problem and supplied candidate interpretations; lexical support does not establish semantic entailment. SchedNL-Bench-Cert contains 1,000 synthetic Chinese/English utterances and 350 sessions. Gold-AST replay measures internal consistency against labels generated by the same engine, while author-written protocol simulations illustrate selected design choices. Across three live-parser seeds on 52 sessions, session training and registered sibling augmentation raise conditional micro target-constraint agreement from 18.0% to 83.7%. The final configuration has 100% coarse status agreement but only 75.0% conflict-member agreement, and includes a rule informed by a test-session failure. We therefore treat these results as descriptive, not as an unbiased generalization estimate. We define a stricter joint-turn criterion and report the bounds supported by the available aggregates. The contribution is a protocol for exposing inspectable solver evidence and the remaining gap between encoded feasibility and user-intent correctness.</abstract>
<identifier type="citekey">yang-etal-2026-cosched</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.24/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>310</start>
<end>321</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoSched-Cert: Faithful Multi-Turn Scheduling Dialogue via Solver-Verified Certificates
%A Yang, Zida
%A Zou, Minhao
%A Peng, Yijie
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F yang-etal-2026-cosched
%X Multi-turn scheduling assistants must preserve constraint edits and distinguish solver evidence from language-model interpretations. We present CoSched-Cert, a dialogue protocol combining a typed scheduling language, solver-distinguishing clarification, cost-based conflict localization, verified repair synthesis, and lexical certificate auditing. Its guarantees are conditional on the encoded problem and supplied candidate interpretations; lexical support does not establish semantic entailment. SchedNL-Bench-Cert contains 1,000 synthetic Chinese/English utterances and 350 sessions. Gold-AST replay measures internal consistency against labels generated by the same engine, while author-written protocol simulations illustrate selected design choices. Across three live-parser seeds on 52 sessions, session training and registered sibling augmentation raise conditional micro target-constraint agreement from 18.0% to 83.7%. The final configuration has 100% coarse status agreement but only 75.0% conflict-member agreement, and includes a rule informed by a test-session failure. We therefore treat these results as descriptive, not as an unbiased generalization estimate. We define a stricter joint-turn criterion and report the bounds supported by the available aggregates. The contribution is a protocol for exposing inspectable solver evidence and the remaining gap between encoded feasibility and user-intent correctness.
%U https://aclanthology.org/2026.groundlm-1.24/
%P 310-321
Markdown (Informal)
[CoSched-Cert: Faithful Multi-Turn Scheduling Dialogue via Solver-Verified Certificates](https://aclanthology.org/2026.groundlm-1.24/) (Yang et al., GroundLM 2026)
ACL