AI News HubLIVE
Original source2 min read

DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues

DuplexGen is a framework that calibrates LLM predictions with a small set of human preference annotations to generate scenario-adaptive turn-taking dialogues. In six cooperative and competitive tasks, it aligns much closer with human preferences than uncalibrated prompting or generic human-human training data, showing that human calibration is key.

SourcearXiv Computational LinguisticsAuthor: Takyoung Kim, Kang-wook Kim, Sang Hoon Woo, Julia Hirschberg, Gunhee Kim, Dilek Hakkani-T\"ur

-->

[Submitted on 28 Jul 2026]

Title:DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues

View a PDF of the paper titled DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues, by Takyoung Kim and 5 other authors

View PDF HTML (experimental)

Abstract:Turn-taking is a central component of full-duplex interaction. Which turn-taking behaviors are appropriate varies with the scenario, yet current models apply a single norm regardless of context. This limitation originates in their training data: human-human speech corpora capture natural timing phenomena but provide little role grounding or scenario-specific norms, while heuristic or prompted synthesis methods inject turn-taking behaviors without basing them on human preferences. We introduce DuplexGen, a framework for generating dialogues with scenario-adaptive turn-taking by calibrating LLM predictions against a small set of slot-level human preference annotations. In six cooperative and competitive tasks, human turn-taking preferences differ systematically, and DuplexGen aligns substantially more closely with those preferences than uncalibrated prompting or training solely on generic human-human data; a full-duplex model trained on DuplexGen-generated data exhibits distinctive, human-preferred turn-taking behaviors. These results show that human calibration, not corpus scale or prompt design alone, is what allows turn-taking synthesis to be scenario-specific.

Comments: Manuscript under review

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2607.26178 [cs.CL]

(or arXiv:2607.26178v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.26178

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Takyoung Kim [view email] [v1] Tue, 28 Jul 2026 18:36:46 UTC (1,658 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues, by Takyoung Kim and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-07

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)