pith. machine review for the scientific record. sign in

arxiv: 2604.16095 · v1 · submitted 2026-04-17 · 💻 cs.HC

Recognition: unknown

GroupEnvoy: A Conversational Agent Speaking for the Outgroup to Foster Intergroup Relations

Koken Hata , Rintaro Chujo , Reina Takamatsu , Wenzhen Xu , Yukino Baba
Authors on Pith no claims yet

Pith reviewed 2026-05-10 08:01 UTC · model grok-4.3

classification 💻 cs.HC
keywords conversational agentsintergroup relationsAI-mediated contactperspective-takingintergroup anxietyoutgroup representationintergroup contact theory
0
0 comments X

The pith

A conversational agent that voices outgroup perspectives during ingroup discussions reduces intergroup anxiety and improves perspective-taking more than reading the same transcripts.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes and tests GroupEnvoy, a conversational agent that speaks for an outgroup by drawing directly from transcripts of outgroup-only sessions. In a study, university students from the host country worked on a task while either hearing the agent deliver those perspectives or reading the transcripts themselves. The agent users showed larger drops in anxiety toward the international students and stronger gains in seeing their viewpoint. The work matters because many groups face barriers to direct contact, and this offers one way to create mediated contact that still draws on real outgroup input. Results also suggest the live delivery shapes different kinds of empathy and future intentions than passive reading.

Core claim

GroupEnvoy is a conversational agent that represents outgroup perspectives during ingroup discussions, grounded in transcripts from outgroup-only sessions. In the mixed-methods between-subjects study, ingroup students using the agent during a collaborative task experienced greater reduction in intergroup anxiety and greater improvement in perspective-taking than those reading written transcripts. Qualitative analysis showed that agent-mediated contact boosted outcome expectancies while passive exposure increased intentions for future contact, and that the two formats elicited empathy toward different targets: outgroup evaluations of the ingroup versus outgroup lived experiences.

What carries the argument

GroupEnvoy, a conversational agent that delivers outgroup perspectives extracted from outgroup-only transcripts to ingroup participants in real time during collaborative tasks.

If this is right

  • AI-mediated contact using outgroup transcripts can produce stronger immediate reductions in anxiety than passive reading of the same material.
  • Delivery format affects which aspects of the outgroup receive empathy: agent use emphasizes outgroup views of the ingroup, while reading emphasizes outgroup experiences.
  • Such agents offer a scalable way to introduce outgroup input when direct intergroup interaction is blocked by psychological or practical barriers.
  • Design choices around conversational versus written presentation influence both short-term attitude change and longer-term contact intentions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The method could extend to workplace or community settings if transcripts are gathered from representative outgroup samples without introducing new selection biases.
  • Testing the agent in repeated sessions over weeks would show whether the anxiety reductions persist or translate into actual cross-group behavior.
  • Integrating the agent into existing group-chat tools might let teams apply the approach without needing a separate study environment.

Load-bearing premise

The measured benefits come from the conversational delivery by the agent rather than from differences in the underlying content or from being in an experimental setting.

What would settle it

A follow-up experiment that holds the exact transcript content fixed and compares only conversational agent delivery against static reading, finding no reliable difference in anxiety reduction or perspective-taking gains.

Figures

Figures reproduced from arXiv: 2604.16095 by Koken Hata, Reina Takamatsu, Rintaro Chujo, Wenzhen Xu, Yukino Baba.

Figure 1
Figure 1. Figure 1: Screenshot of the GroupEnvoy chat interface. Mes [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Mean scores (with ±1 SE error bars) for each psychological measure at pre- and post-test, by condition. All measures used a 7-point Likert scale. FCI = Future Contact Intentions. Attitudes = Outgroup attitudes [PITH_FULL_IMAGE:figures/full_fig_p009_2.png] view at source ↗
read the original abstract

Conversational agents have the potential to support intergroup relations when psychological or linguistic barriers prevent direct interaction. Based on intergroup contact theory, we propose GroupEnvoy, a conversational agent that represents outgroup perspectives during ingroup discussions, grounded in transcripts from outgroup-only sessions. To evaluate this approach and derive design principles, we conducted a mixed-methods, between-subjects study with university students, where host-country students formed the ingroup and international students formed the outgroup. Ingroup students performed a collaborative task, receiving outgroup perspectives via GroupEnvoy (experimental) or reading written transcripts (control). Compared to the control group, the experimental group showed greater reduction in intergroup anxiety and greater improvement in perspective-taking. Qualitatively, AI-mediated contact enhanced outcome expectancies, whereas passive exposure fostered future contact intentions. The two conditions also elicited empathy toward distinct targets: outgroup evaluations of the ingroup versus outgroup lived experiences. These findings validate AI-mediated contact as a promising paradigm for improving intergroup relations.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper proposes GroupEnvoy, a conversational agent that voices outgroup perspectives (drawn from outgroup-only transcripts) during ingroup collaborative discussions to improve intergroup relations. It reports a mixed-methods between-subjects study with university students (host-country ingroup vs. international outgroup) comparing the agent condition against passive reading of written transcripts on the same task. Key results include greater reductions in intergroup anxiety and greater gains in perspective-taking for the experimental group, plus qualitative differences in empathy targets, outcome expectancies, and future contact intentions.

Significance. If the quantitative and qualitative results hold after addressing reporting gaps, the work offers a novel HCI contribution by extending intergroup contact theory to AI-mediated formats, particularly useful when direct contact faces barriers. The mixed-methods approach yields both outcome measures and design insights, with potential for broader applications in conflict resolution or diversity training.

major comments (3)
  1. [Methods (study procedure)] Methods section (study procedure): The control condition is described as reading written transcripts, but the manuscript does not confirm that the exact wording, length, selection criteria, and emphasis of the transcripts provided to controls are identical to the material voiced by GroupEnvoy (including any agent summarization or excerpt choice). This is load-bearing for the central claim, as any content mismatch would confound format effects with content differences and prevent isolating the conversational delivery benefit.
  2. [Results (quantitative findings)] Results section (quantitative findings): The abstract states directional improvements in intergroup anxiety reduction and perspective-taking but the manuscript provides no sample size (N), pre/post means, statistical tests (e.g., t-test or mixed ANOVA), p-values, effect sizes, or power analysis. Without these details, the magnitude, reliability, and practical significance of the between-group differences cannot be assessed, weakening the data-to-claim link.
  3. [Introduction and Design rationale] Design rationale (introduction and §3): The assumption that outgroup perspectives are representative and unbiased rests on their derivation from outgroup-only transcripts, yet the paper does not detail transcript sampling procedures, randomization of excerpts, or checks that the agent does not introduce selection bias absent in the control. This directly affects the weakest assumption identified in the skeptic note and the validity of attributing benefits to the agent format.
minor comments (2)
  1. [Abstract] The abstract would be strengthened by briefly noting the sample size and key statistical outcomes to allow readers to gauge effect strength without reading the full results.
  2. [Qualitative analysis] Qualitative themes on empathy targets (outgroup evaluations of ingroup vs. lived experiences) are interesting but would benefit from more explicit linkage to specific participant quotes or coding scheme details for reproducibility.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their constructive comments, which help us clarify key aspects of the study design and reporting. We address each major comment below and will revise the manuscript to incorporate the necessary details.

read point-by-point responses

  1. Referee: Methods section (study procedure): The control condition is described as reading written transcripts, but the manuscript does not confirm that the exact wording, length, selection criteria, and emphasis of the transcripts provided to controls are identical to the material voiced by GroupEnvoy (including any agent summarization or excerpt choice). This is load-bearing for the central claim, as any content mismatch would confound format effects with content differences and prevent isolating the conversational delivery benefit.

    Authors: We agree that matching the content between conditions is essential to attribute differences to the conversational format rather than content variations. The transcripts used in both conditions were derived from the same outgroup-only sessions, with identical excerpts selected based on relevance to the collaborative task. The agent voiced these excerpts directly without additional summarization or alteration. We will revise the Methods section to explicitly describe the transcript selection process, confirm identical content across conditions, and detail the absence of differential summarization. revision: yes

  2. Referee: Results section (quantitative findings): The abstract states directional improvements in intergroup anxiety reduction and perspective-taking but the manuscript provides no sample size (N), pre/post means, statistical tests (e.g., t-test or mixed ANOVA), p-values, effect sizes, or power analysis. Without these details, the magnitude, reliability, and practical significance of the between-group differences cannot be assessed, weakening the data-to-claim link.

    Authors: We acknowledge that the current manuscript lacks sufficient statistical details in the reporting of quantitative results. The study was conducted with a specific sample size, and appropriate statistical analyses were performed. We will expand the Results section to include the sample size (N), pre- and post-intervention means with standard deviations, details of the statistical tests used (such as t-tests or mixed ANOVA), p-values, effect sizes, and a post-hoc power analysis to allow full assessment of the findings' reliability and practical significance. revision: yes

  3. Referee: Design rationale (introduction and §3): The assumption that outgroup perspectives are representative and unbiased rests on their derivation from outgroup-only transcripts, yet the paper does not detail transcript sampling procedures, randomization of excerpts, or checks that the agent does not introduce selection bias absent in the control. This directly affects the weakest assumption identified in the skeptic note and the validity of attributing benefits to the agent format.

    Authors: We appreciate the emphasis on transparency regarding transcript sampling to support the representativeness claim. The outgroup transcripts were collected from separate sessions with international students, and excerpts were selected based on predefined criteria related to the task topics. To address potential bias, we will add details in the Design and Methods sections on the sampling procedure, including how excerpts were chosen and any randomization applied for presentation, and steps to ensure consistency between the agent-voiced content and the control transcripts. This will strengthen the methodological rigor. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical comparison without models or self-referential predictions

full rationale

The paper reports a mixed-methods between-subjects experiment comparing GroupEnvoy (agent delivering outgroup perspectives from transcripts) against passive reading of written transcripts. Outcomes are measured as observed differences in intergroup anxiety and perspective-taking with no equations, fitted parameters, derived predictions, or load-bearing self-citations. The central claims rest on direct empirical contrasts and qualitative themes rather than any derivation that reduces to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 1 invented entities

The claim rests on the applicability of intergroup contact theory to an AI-mediated format and on the assumption that outgroup transcripts provide faithful input for the agent.

axioms (2)
  • domain assumption Positive intergroup contact reduces prejudice and anxiety when certain conditions are met
    Invoked to justify why outgroup perspectives should improve ingroup outcomes
  • domain assumption Transcripts from outgroup-only sessions accurately and representatively capture outgroup perspectives
    Used to ground the content delivered by GroupEnvoy
invented entities (1)
  • GroupEnvoy no independent evidence
    purpose: Conversational agent that inserts outgroup perspectives into ingroup discussions
    New system created for the study

pith-pipeline@v0.9.0 · 5490 in / 1328 out tokens · 42716 ms · 2026-05-10T08:01:30.927134+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

83 extracted references · 59 canonical work pages · 1 internal anchor

  1. [1]

    Aberson and Sarah C

    Christopher L. Aberson and Sarah C. Haag. 2007. Contact, Perspective Taking, and Anxiety as Predictors of Stereotype Endorsement, Explicit Attitudes, and Implicit Attitudes.Group Processes & Intergroup Relations10, 2 (April 2007), 179–201. doi:10.1177/1368430207074726 Publisher: SAGE Publications Ltd

    work page doi:10.1177/1368430207074726 2007

  2. [2]

    Icek Ajzen. 1991. The theory of planned behavior.Organizational behavior and human decision processes50, 2 (1991), 179–211. https://www.sciencedirect.com/ science/article/pii/074959789190020T Publisher: Elsevier

    work page arXiv 1991

  3. [3]

    Ananthi Al Ramiah and Miles Hewstone. 2013. Intergroup contact as a tool for reducing, resolving, and preventing intergroup conflict: Evidence, limitations, and potential.American Psychologist68, 7 (2013), 527–542. doi:10.1037/a0032603

    work page doi:10.1037/a0032603 2013

  4. [4]

    Pettigrew

    Gordon Willard Allport, Kenneth Clark, and Thomas F. Pettigrew. 1954.The nature of prejudice. Vol. 2. Addison-wesley Reading, MA

    1954

  5. [5]

    Yair Amichai-Hamburger and Katelyn Y. A. McKenna. 2006. The Contact Hypoth- esis Reconsidered: Interacting via the Internet.Journal of Computer-Mediated Communication11, 3 (April 2006), 825–843. doi:10.1111/j.1083-6101.2006.00037.x

    work page doi:10.1111/j.1083-6101.2006.00037.x 2006

  6. [6]

    Hanumanthu, and Mel Slater

    Domna Banakou, Parasuram D. Hanumanthu, and Mel Slater. 2016. Virtual Embodiment of White People in a Black Virtual Body Leads to a Sustained Reduction in Their Implicit Racial Bias.Frontiers in Human Neuroscience10 (Nov. 2016). doi:10.3389/fnhum.2016.00601

    work page doi:10.3389/fnhum.2016.00601 2016

  7. [7]

    C Daniel Batson, Marina R Polycarpou, Eddie Harmon-Jones, Heidi J Imhoff, Erin C Mitchener, Lori L Bednar, Tricia R Klein, and Lori Highberger. 1997. Empathy and Attitudes: Can Feeling for a Member of a Stigmatized Group Improve Feelings Toward the Group? (1997)

    1997

  8. [8]

    Virginia Braun and Victoria Clarke. 2023. Toward good practice in the- matic analysis: Avoiding common problems and be(com)ing a knowing re- searcher.International Journal of Transgender Health24, 1 (Jan. 2023), 1–

    2023

  9. [9]

    doi:10.1080/26895269.2022.2129597 Publisher: Taylor & Francis _eprint: https://doi.org/10.1080/26895269.2022.2129597

    work page doi:10.1080/26895269.2022.2129597 2022

  10. [10]

    David Broockman and Joshua Kalla. 2016. Durably reducing transphobia: A field experiment on door-to-door canvassing.Science352, 6282 (April 2016), 220–224. doi:10.1126/science.aad9713

    work page doi:10.1126/science.aad9713 2016

  11. [11]

    Joanna Brooks, Serena McCluskey, Emma Turley, and Nigel King. 2015. The Utility of Template Analysis in Qualitative Psychology Research.Qualitative Research in Psychology12, 2 (April 2015), 202–222. doi:10.1080/14780887.2014. 955224

    work page doi:10.1080/14780887.2014 2015

  12. [12]

    Rupert Brown and Miles Hewstone. 2005. An integrative theory of intergroup contact. InAdvances in Experimental Social Psychology. Vol. 37. Elsevier, 255–343. doi:10.1016/S0065-2601(05)37005-5

    work page doi:10.1016/s0065-2601(05)37005-5 2005

  13. [13]

    Bruneau and Rebecca Saxe

    Emile G. Bruneau and Rebecca Saxe. 2012. The power of being heard: The benefits of ‘perspective-giving’ in the context of intergroup conflict.Journal of Experimental Social Psychology48, 4 (July 2012), 855–866. doi:10.1016/j.jesp.2012. 02.017

    work page doi:10.1016/j.jesp.2012 2012

  14. [14]

    Chun-Wei Chiang, Zhuoran Lu, Zhuoyan Li, and Ming Yin. 2024. Enhancing AI-Assisted Group Decision Making through LLM-Powered Devil’s Advocate. InProceedings of the 29th International Conference on Intelligent User Interfaces. ACM, Greenville SC USA, 103–119. doi:10.1145/3640543.3645199

    work page doi:10.1145/3640543.3645199 2024

  15. [15]

    2018.Qualitative Method- ologies in Organization Studies

    Malgorzata Ciesielska and Dariusz Jemielniak (Eds.). 2018.Qualitative Method- ologies in Organization Studies. Springer International Publishing, Cham. doi:10.1007/978-3-319-65442-3

    work page doi:10.1007/978-3-319-65442-3 2018

  16. [16]

    2013.Statistical power analysis for the behavioral sciences

    Jacob Cohen. 1988.Statistical power analysis for the behavioral sciences. routledge. https://api.taylorfrancis.com/content/books/mono/download? identifierName=doi&identifierValue=10.4324/9780203771587&type=googlepdf

    work page doi:10.4324/9780203771587 1988

  17. [17]

    Charles Crabtree, John Holbein, Mitchell Bosley, and Semra Sevi. 2025. Can AI Help Reduce Prejudice? Evaluating the Effectiveness of AI-Powered Personalized Persuasion on Support for Transgender Rights.Evaluating the Effectiveness of AI-Powered Personalized Persuasion on Support for Transgender Rights (April 24, 2025)(2025). https://papers.ssrn.com/sol3/p...

    2025

  18. [18]

    Mark H. A. Davis. 1994.Empathy: a social psychological approach. Routledge, New York Abingdon

    1994

  19. [19]

    Dovidio, Angelika Love, Fabian M

    John F. Dovidio, Angelika Love, Fabian M. H. Schellhaas, and Miles Hewstone

  20. [20]

    2017), 606–620

    Reducing intergroup bias through intergroup contact: Twenty years of progress and future directions.Group Processes & Intergroup Relations20, 5 (Sept. 2017), 606–620. doi:10.1177/1368430217712052

    work page doi:10.1177/1368430217712052 2017

  21. [21]

    Frey and Linda R

    Frances E. Frey and Linda R. Tropp. 2006. Being Seen As Individuals Versus As Group Members: Extending Research on Metaperception to Intergroup Contexts. Personality and Social Psychology Review10, 3 (Aug. 2006), 265–280. doi:10.1207/ s15327957pspr1003_5 Publisher: SAGE Publications Inc

    2006

  22. [22]

    Galinsky, Gillian Ku, and Cynthia S

    Adam D. Galinsky, Gillian Ku, and Cynthia S. Wang. 2005. Perspective-Taking and Self-Other Overlap: Fostering Social Bonds and Facilitating Social Coordination. Group Processes & Intergroup Relations8, 2 (April 2005), 109–124. doi:10.1177/ 1368430205051060

    2005

  23. [23]

    Outcome Questionnaire: Is It Sensitive to Changes in Counseling Center Clients? Journal of Counseling Psychology, 51(1), 38–49

    Adam D. Galinsky and Gordon B. Moskowitz. 2000. Perspective-taking: Decreas- ing stereotype expression, stereotype accessibility, and in-group favoritism.Jour- nal of Personality and Social Psychology78, 4 (2000), 708–724. doi:10.1037/0022- 3514.78.4.708

    work page doi:10.1037/0022- 2000

  24. [24]

    2025.Gemini 3 Pro Model Card

    Gemini Team. 2025.Gemini 3 Pro Model Card. Technical Report. Google Deep- Mind. https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini- 3-Pro-Model-Card.pdf

    2025

  25. [25]

    Katy Greenland, Dimitrios Xenias, and Greg Maio. 2012. Intergroup anxiety from the self and other: Evidence from self-report, physiological effects, and real interactions.European Journal of Social Psychology42, 2 (2012), 150–163. doi:10. 1002/ejsp.867 _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/ejsp.867

    work page doi:10.1002/ejsp.867 2012

  26. [26]

    Jeffrey T Hancock, Mor Naaman, and Karen Levy. 2020. AI-Mediated Commu- nication: Definition, Research Agenda, and Ethical Considerations.Journal of Computer-Mediated Communication25, 1 (March 2020), 89–100. doi:10.1093/ jcmc/zmz022

    2020

  27. [27]

    Jake Harwood, Miles Hewstone, Stefania Paolini, and Alberto Voci. 2005. Grandparent-Grandchild Contact and Attitudes Toward Older Adults: Moderator Koken Hata, Rintaro Chujo, Reina Takamatsu, Wenzhen Xu, and Yukino Baba and Mediator Effects.Personality and Social Psychology Bulletin31, 3 (March 2005), 393–406. doi:10.1177/0146167204271577 Publisher: SAGE ...

    work page doi:10.1177/0146167204271577 2005

  28. [28]

    Erik Hermann, Julian De Freitas, and Stefano Puntoni. 2025. Reducing prejudice with counter-stereotypical AI.Consumer Psychology Review8, 1 (Jan. 2025), 75–86. doi:10.1002/arcp.1102

    work page doi:10.1002/arcp.1102 2025

  29. [29]

    Miles Hewstone and Rupert Brown. 1986. Contact is not enough: An intergroup perspective on the’contact hypothesis. ’. (1986). https://psycnet.apa.org/record/ 1989-97053-001 Publisher: Basil Blackwell

    1986

  30. [30]

    Senel Husnu and Richard J. Crisp. 2010. Elaboration enhances the imagined contact effect.Journal of Experimental Social Psychology46, 6 (Nov. 2010), 943–

    2010

  31. [31]

    doi:10.1016/j.jesp.2010.05.014

    work page doi:10.1016/j.jesp.2010.05.014 2010

  32. [32]

    Schneider, Luca Caricati, Yair Amichai-Hamburger, and Tiziana Mancini

    Chiara Imperato, Barry H. Schneider, Luca Caricati, Yair Amichai-Hamburger, and Tiziana Mancini. 2021. Allport meets internet: A meta-analytical investiga- tion of online intergroup contact and prejudice reduction.International Journal of Intercultural Relations81 (March 2021), 131–141. doi:10.1016/j.ijintrel.2021.01.006

    work page doi:10.1016/j.ijintrel.2021.01.006 2021

  33. [33]

    Hancock, and Mor Naaman

    Maurice Jakesch, Megan French, Xiao Ma, Jeffrey T. Hancock, and Mor Naaman

  34. [34]

    InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems

    AI-Mediated Communication: How the Perception that Profile Text was Written by AI Affects Trustworthiness. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems. ACM, Glasgow Scotland Uk, 1–13. doi:10.1145/3290605.3300469

    work page doi:10.1145/3290605.3300469 2019

  35. [35]

    Lucy Johnston and Miles Hewstone. 1992. Cognitive models of stereotype change.Journal of Experimental Social Psychology28, 4 (July 1992), 360–386. doi:10.1016/0022-1031(92)90051-K

    work page doi:10.1016/0022-1031(92)90051-k 1992

  36. [36]

    Hyuntak Kim and Byung-Hak Kim. 2025. NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization. InProceedings of the 63rd Annual Meet- ing of the Association for Computational Linguistics (Volume 1: Long Papers), Wanx- iang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar (Eds.). Association for Computational Linguistics, V...

    work page doi:10.18653/v1/2025.acl-long.500 2025

  37. [37]

    Nuri Kim and Magdalena Wojcieszak. 2018. Intergroup contact through online comments: Effects of direct and extended contact on outgroup attitudes.Com- puters in Human Behavior81 (April 2018), 63–72. doi:10.1016/j.chb.2017.11.013

    work page doi:10.1016/j.chb.2017.11.013 2018

  38. [38]

    Soomin Kim, Jinsu Eun, Joseph Seering, and Joonhwan Lee. 2021. Moderator Chatbot for Deliberative Discussion: Effects of Discussion Structure and Dis- cussant Facilitation.Proceedings of the ACM on Human-Computer Interaction5, CSCW1 (April 2021), 1–26. doi:10.1145/3449161

    work page doi:10.1145/3449161 2021

  39. [39]

    Procaccia, Lisa Schirch, and Michiel A

    Andrew Konya, Luke Thorburn, Wasim Almasri, Oded Adomi Leshem, Ariel D. Procaccia, Lisa Schirch, and Michiel A. Bakker. 2025. Using Collective Dialogues and AI to Find Common Ground Between Israeli and Palestinian Peacebuilders. doi:10.48550/arXiv.2503.01769 arXiv:2503.01769 [cs] version: 1

    work page doi:10.48550/arxiv.2503.01769 2025

  40. [40]

    Soohwan Lee, Seoyeong Hwang, Dajung Kim, and Kyungho Lee. 2025. Conver- sational Agents as Catalysts for Critical Thinking: Challenging Social Influence in Group Decision-making. InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. ACM, Yokohama Japan, 1–12. doi:10.1145/3706599.3719792

    work page doi:10.1145/3706599.3719792 2025

  41. [41]

    SooHwan Lee, Mingyu Kim, Seoyeong Hwang, Dajung Kim, and Kyungho Lee

  42. [42]

    InCompanion Proceedings of the 30th Inter- national Conference on Intelligent User Interfaces

    Amplifying Minority Voices: AI-Mediated Devil’s Advocate System for Inclusive Group Decision-Making. InCompanion Proceedings of the 30th Inter- national Conference on Intelligent User Interfaces. ACM, Cagliari Italy, 17–21. doi:10.1145/3708557.3716334

    work page doi:10.1145/3708557.3716334

  43. [43]

    Shuai Ma, Qiaoyi Chen, Xinru Wang, Chengbo Zheng, Zhenhui Peng, Ming Yin, and Xiaojuan Ma. 2024. Towards Human-Ai Deliberation: Design and Evaluation of Llm-Empowered Deliberative Ai for Ai-Assisted Decision-Making. doi:10.2139/ssrn.4772689

    work page doi:10.2139/ssrn.4772689 2024

  44. [44]

    Lars Malmqvist. 2024. Sycophancy in Large Language Models: Causes and Mitigations. doi:10.48550/arXiv.2411.15287 arXiv:2411.15287 [cs]

    work page doi:10.48550/arxiv.2411.15287 2024

  45. [45]

    Norman Miller. 2002. Personalization and the Promise of Contact Theory.Journal of Social Issues58, 2 (2002), 387–410. doi:10.1111/1540-4560.00267 _eprint: https://spssi.onlinelibrary.wiley.com/doi/pdf/10.1111/1540-4560.00267

    work page doi:10.1111/1540-4560.00267 2002

  46. [46]

    Serge Moscovici and Marisa Zavalloni. 1969. The group as a polarizer of attitudes. Journal of personality and social psychology12, 2 (1969), 125. https://psycnet. apa.org/journals/psp/12/2/125/ Publisher: American Psychological Association

    1969

  47. [47]

    White, Linda R

    Stefania Paolini, Fiona A. White, Linda R. Tropp, Rhiannon N. Turner, Elizabeth Page-Gould, Fiona K. Barlow, and Ángel Gómez. 2021. Intergroup contact re- search in the 21st century: Lessons learned and forward progress if we remain open.Journal of Social Issues77, 1 (2021), 11–37. doi:10.1111/josi.12427 _eprint: https://spssi.onlinelibrary.wiley.com/doi/...

    work page doi:10.1111/josi.12427 2021

  48. [48]

    Wright, Odilia Dys-Steenbergen, and Irene Favara

    Stefania Paolini, Stephen C. Wright, Odilia Dys-Steenbergen, and Irene Favara

  49. [49]

    doi:10.1111/josi

    Self-Expansion and Intergroup Contact: Expectancies and Motives to Self-Expand Lead to Greater Interest in Outgroup Contact and More Positive In- tergroup Relations.Journal of Social Issues72, 3 (2016), 450–471. doi:10.1111/josi. 12176 _eprint: https://spssi.onlinelibrary.wiley.com/doi/pdf/10.1111/josi.12176

    work page doi:10.1111/josi 2016

  50. [50]

    Leonor Pereira Da Costa, Kinga Bierwiaczonek, and Mauro Bianchi. 2024. Does Digital Intergroup Contact Reduce Prejudice? A Meta-Analysis.Cyberpsychology, Behavior, and Social Networking27, 7 (July 2024), 440–451. doi:10.1089/cyber. 2023.0591

    work page doi:10.1089/cyber 2024

  51. [51]

    Pettigrew

    Thomas F. Pettigrew. 1998. INTERGROUP CONTACT THEORY.Annual Review of Psychology49, 1 (Feb. 1998), 65–85. doi:10.1146/annurev.psych.49.1.65

    work page doi:10.1146/annurev.psych.49.1.65 1998

  52. [52]

    Pettigrew and Linda R

    Thomas F. Pettigrew and Linda R. Tropp. 2006. A meta-analytic test of intergroup contact theory.Journal of Personality and Social Psychology90, 5 (2006), 751–783. doi:10.1037/0022-3514.90.5.751

    work page doi:10.1037/0022-3514.90.5.751 2006

  53. [53]

    Pettigrew and Linda R

    Thomas F. Pettigrew and Linda R. Tropp. 2008. How does intergroup contact reduce prejudice? Meta-analytic tests of three mediators.European Journal of Social Psychology38, 6 (Sept. 2008), 922–934. doi:10.1002/ejsp.504

    work page doi:10.1002/ejsp.504 2008

  54. [54]

    Ashby Plant

    E. Ashby Plant. 2004. Responses to Interracial Interactions Over Time.Person- ality and Social Psychology Bulletin30, 11 (Nov. 2004), 1458–1471. doi:10.1177/ 0146167204264244

    2004

  55. [55]

    Ashby Plant and Patricia G

    E. Ashby Plant and Patricia G. Devine. 2003. The Antecedents and Implications of Interracial Anxiety.Personality and Social Psychology Bulletin29, 6 (June 2003), 790–801. doi:10.1177/0146167203029006011

    work page doi:10.1177/0146167203029006011 2003

  56. [56]

    Sofia Sahab, Jawad Haqbeen, Rafik Hadfi, Takayuki Ito, Richard Eke Imade, Susumu Ohnuma, and Takuya Hasegawa. 2024. E-contact facilitated by conver- sational agents reduces interethnic prejudice and anxiety in Afghanistan.Com- munications Psychology2, 1 (March 2024), 22. doi:10.1038/s44271-024-00070-z

    work page doi:10.1038/s44271-024-00070-z 2024

  57. [57]

    Tomomi Sakakibara. 2017. Intercultural Understanding through Intergroup Dialogue between Japanese and Chinese University Students.Integrative Psycho- logical and Behavioral Science51, 3 (Sept. 2017), 359–378. doi:10.1007/s12124- 017-9390-x

    work page doi:10.1007/s12124- 2017

  58. [58]

    Schlenker and Mark R

    Barry R. Schlenker and Mark R. Leary. 1982. Social anxiety and self-presentation: A conceptualization model.Psychological bulletin92, 3 (1982), 641. https: //psycnet.apa.org/record/1983-05605-001 Publisher: American Psychological Association

    1982

  59. [59]

    1904.01361

    Mrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R. Bowman, Newton Cheng, Esin Durmus, Zac Hatfield-Dodds, Scott R. Johnston, Shauna Kravec, Timothy Maxwell, Sam McCandlish, Kamal Ndousse, Oliver Rausch, Nicholas Schiefer, Da Yan, Miranda Zhang, and Ethan Perez. 2023. Towards Understanding Sycophancy in Language Models. doi:1...

    work page internal anchor Pith review doi:10.48550/arxiv 2023

  60. [60]

    Stephan and Cookie White Stephan

    Walter G. Stephan and Cookie White Stephan. 1985. Intergroup Anxiety. Journal of Social Issues41, 3 (1985), 157–175. doi:10.1111/j.1540-4560.1985. tb01134.x _eprint: https://spssi.onlinelibrary.wiley.com/doi/pdf/10.1111/j.1540- 4560.1985.tb01134.x

    work page doi:10.1111/j.1540-4560.1985 1985

  61. [61]

    Stephan, Walter G. 1999. A Survey for Use in Evaluating Dialogue Programs. https://www.ncdd.org/uploads/1/3/5/5/135559674/walter_stephan.pdf

    1999

  62. [62]

    Hermann Swart, Miles Hewstone, Oliver Christ, and Alberto Voci. 2011. Affective mediators of intergroup contact: a three-wave longitudinal study in South Africa. Journal of personality and social psychology101, 6 (2011), 1221. https://psycnet. apa.org/record/2011-13616-001 Publisher: American Psychological Association

    2011

  63. [63]

    Atsushi Tajima and Yingmin Jiang. 2025. An educational program addressing tense intercultural communication between Japanese and Chinese students: A Bakhtinian perspective on dialogue and love.Dialogic Pedagogy: A Journal for Studies of Dialogic Education13, 1 (March 2025), PLC1–PLC20. doi:10.5195/dpj. 2025.601

    work page doi:10.5195/dpj 2025

  64. [64]

    Bakker, Daniel Jarrett, Hannah Sheahan, Martin J

    Michael Henry Tessler, Michiel A. Bakker, Daniel Jarrett, Hannah Sheahan, Mar- tin J. Chadwick, Raphael Koster, Georgina Evans, Lucy Campbell-Gillingham, Tantum Collins, David C. Parkes, Matthew Botvinick, and Christopher Summer- field. 2024. AI can help humans find common ground in democratic deliberation. Science386, 6719 (Oct. 2024), eadq2852. doi:10.1...

    work page doi:10.1126/science.adq2852 2024

  65. [65]

    Richeson, and J

    Sophie Trawalter, Jennifer A. Richeson, and J. Nicole Shelton. 2009. Pre- dicting Behavior During Interracial Interactions: A Stress and Coping Ap- proach.Personality and Social Psychology Review13, 4 (Nov. 2009), 243–268. doi:10.1177/1088868309345850 Publisher: SAGE Publications Inc

    work page doi:10.1177/1088868309345850 2009

  66. [66]

    Turner, Richard J

    Rhiannon N. Turner, Richard J. Crisp, and Emily Lambert. 2007. Imagining Inter- group Contact Can Improve Intergroup Attitudes.Group Processes & Intergroup Relations10, 4 (Oct. 2007), 427–441. doi:10.1177/1368430207081533

    work page doi:10.1177/1368430207081533 2007

  67. [67]

    Turner, Miles Hewstone, Alberto Voci, and Christiana Vonofakou

    Rhiannon N. Turner, Miles Hewstone, Alberto Voci, and Christiana Vonofakou

  68. [68]

    2008), 843–860

    A test of the extended intergroup contact hypothesis: The mediating role of intergroup anxiety, perceived ingroup and outgroup norms, and inclusion of the outgroup in the self.Journal of Personality and Social Psychology95, 4 (Oct. 2008), 843–860. doi:10.1037/a0011434 Publisher: American Psychological Association

    work page doi:10.1037/a0011434 2008

  69. [69]

    Ugarriza and Enzo Nussio

    Juan E. Ugarriza and Enzo Nussio. 2017. The Effect of Perspective- Giving on Postconflict Reconciliation. An Experimental Approach.Po- litical Psychology38, 1 (2017), 3–19. doi:10.1111/pops.12324 _eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1111/pops.12324

    work page doi:10.1111/pops.12324 2017

  70. [70]

    Alberto Voci and Miles Hewstone. 2003. Intergroup Contact and Prejudice To- ward Immigrants in Italy: The Mediational Role of Anxiety and the Moderational Role of Group Salience.Group Processes & Intergroup Relations6, 1 (Jan. 2003), 37–54. doi:10.1177/1368430203006001011 Publisher: SAGE Publications Ltd

    work page doi:10.1177/1368430203006001011 2003

  71. [71]

    Yi Wang and Min Zhang. 2020. Reducing implicit gender biases in software de- velopment: does intergroup contact theory work?. InProceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2020). Association for Computing Machinery, New York, NY, USA, 580–592. doi:...

    work page doi:10.1145/3368089.3409762 2020

  72. [72]

    White and Hisham M

    Fiona A. White and Hisham M. Abu-Rayya. 2012. A dual identity-electronic contact (DIEC) experiment promoting short- and long-term intergroup harmony. Journal of Experimental Social Psychology48, 3 (May 2012), 597–608. doi:10.1016/ j.jesp.2012.01.007

    2012

  73. [73]

    White, Islam Borinca, Loris Vezzali, Katherine J

    Fiona A. White, Islam Borinca, Loris Vezzali, Katherine J. Reynolds, Johanna K. Blomster Lyshol, Stefano Verrelli, and Juan M. Falomir- Pichastor. 2021. Beyond direct contact: The theoretical and societal rel- evance of indirect contact for improving intergroup relations.Journal of Social Issues77, 1 (2021), 132–153. doi:10.1111/josi.12400 _eprint: https:...

    work page doi:10.1111/josi.12400 2021

  74. [74]

    White, Lauren J

    Fiona A. White, Lauren J. Harvey, and Hisham M. Abu-Rayya. 2015. Improving Intergroup Relations in the Internet Age: A Critical Review.Review of General Psychology19, 2 (June 2015), 129–139. doi:10.1037/gpr0000036 Publisher: SAGE Publications Inc

    work page doi:10.1037/gpr0000036 2015

  75. [75]

    White, Rachel Maunder, and Stefano Verrelli

    Fiona A. White, Rachel Maunder, and Stefano Verrelli. 2020. Text-based E-contact: Harnessing cooperative Internet interactions to bridge the social and psychological divide.European Review of Social Psychology31, 1 (Jan. 2020), 76–119. doi:10.1080/10463283.2020.1753459 Publisher: Routledge _eprint: https://doi.org/10.1080/10463283.2020.1753459

    work page doi:10.1080/10463283.2020.1753459 2020

  76. [76]

    White, Rhiannon N

    Fiona A. White, Rhiannon N. Turner, Stefano Verrelli, Lauren J. Harvey, and Jeffrey R. Hanna. 2019. Improving intergroup relations between Catholics and Protestants in Northern Ireland via E-contact.European Journal of Social Psy- chology49, 2 (March 2019), 429–438. doi:10.1002/ejsp.2515

    work page doi:10.1002/ejsp.2515 2019

  77. [77]

    David A Wilder. 1984. Intergroup contact: The typical member and the exception to the rule.Journal of Experimental Social Psychology20, 2 (March 1984), 177–194. doi:10.1016/0022-1031(84)90019-2

    work page doi:10.1016/0022-1031(84)90019-2 1984

  78. [78]

    Wout, Mary C

    Daryl A. Wout, Mary C. Murphy, and Claude M. Steele. 2010. When your friends matter: The effect of White students’ racial friendship networks on meta- perceptions and perceived identity contingencies.Journal of Experimental Social Psychology46, 6 (Nov. 2010), 1035–1041. doi:10.1016/j.jesp.2010.06.003

    work page doi:10.1016/j.jesp.2010.06.003 2010

  79. [79]

    Wright, Arthur Aron, Tracy McLaughlin-Volpe, and Stacy A

    Stephen C. Wright, Arthur Aron, Tracy McLaughlin-Volpe, and Stacy A. Ropp

  80. [80]

    doi:10.1037/0022-3514.73.1.73 Publisher: American Psychological Association

    The extended contact effect: Knowledge of cross-group friendships and prejudice.Journal of Personality and Social Psychology73, 1 (July 1997), 73–90. doi:10.1037/0022-3514.73.1.73 Publisher: American Psychological Association

    work page doi:10.1037/0022-3514.73.1.73 1997

Showing first 80 references.