pith. sign in

arxiv: 2605.30930 · v1 · pith:NWP5UMALnew · submitted 2026-05-29 · 💻 cs.HC · cs.AI· cs.CL· cs.CY

TUX: Measuring Human--AI Tacit Understanding

Yueshen Li , Hanyi Min , Vedant Das Swain , Koustuv Saha This is my paper

Pith reviewed 2026-06-28 21:16 UTC · model grok-4.3

classification 💻 cs.HC cs.AIcs.CLcs.CY
keywords human-AI alignmenttacit understandingLLM agentspersonality traitsspectrum placementTUX indexWavelength task
0
0 comments X

The pith

Human-AI pairs nearest in trait space achieve significantly higher tacit understanding on independent spectrum placements.

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

The paper introduces a spectrum-placement task modeled on the game Wavelength in which humans and profile-conditioned LLMs each locate concepts along subjective dimensions without communication or shared goals. It defines the Tacit Understanding Index (TUX) as the degree of similarity between those independent placements. Across 241 human participants and 200 LLM agents, the study finds that pairs closest in measured personality traits produce reliably higher TUX scores than more distant pairs. Regression models further show that adding individual traits, decision styles, and confidence levels improves the ability to predict TUX beyond simple aggregate distance. These results indicate that tacit alignment between people and language models follows structured person-level characteristics rather than occurring at random.

Core claim

We operationalize tacit understanding as pairwise similarity in human and agent judgments on a spectrum-placement task performed without objectives, communication, or feedback. The resulting TUX measure is significantly higher for human-agent pairs nearest in trait space. Richer predictor sets that include individual traits, decision-making styles, and confidence explain more variance in TUX than baseline trait-distance models, while profile conditioning alone shows limits in capturing deeper representational alignment.

What carries the argument

The Tacit Understanding Index (TUX), computed as pairwise similarity between independent human and LLM placements of concepts along subjective spectra.

If this is right

  • Tacit alignment between humans and LLMs is organized by person-level characteristics instead of random similarity.
  • Richer sets of individual predictors improve explanation of TUX beyond aggregate trait distance.
  • Profile conditioning on LLMs reaches limits in producing deeper representational alignment.
  • TUX rises as matching incorporates traits, decision styles, and confidence.

Where Pith is reading between the lines

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

  • Matching agents to humans on detailed trait profiles could raise tacit alignment in collaborative settings.
  • The spectrum task might be adapted to measure unspoken alignment in creative or decision-making domains.
  • Alternative conditioning methods beyond static profiles could be tested to close the observed gaps in TUX.

Load-bearing premise

The spectrum-placement task validly captures tacit understanding through similarity of judgments made without clear objectives, communication, or feedback.

What would settle it

Finding no reliable TUX advantage for nearest-trait human-agent pairs compared with random or distant pairs would falsify the claim that tacit alignment is structured by person-level traits.

Figures

Figures reproduced from arXiv: 2605.30930 by Hanyi Min, Koustuv Saha, Vedant Das Swain, Yueshen Li.

Figure 1
Figure 1. Figure 1: A schematic figure of our study design: Human participants and profile-conditioned LLM agents complete [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Interface of the spectrum placement task. [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Matched-versus-random TUX distributions. [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
read the original abstract

As large language models (LLMs) increasingly act as collaborative partners, human--AI alignment is often evaluated through explicit task success, accuracy, or reward optimization. Yet many collaborative settings depend on tacit understanding: whether an agent can align with a human's evaluative stance or representational priors without clear objectives, communication, or feedback. To study this capacity, we develop a spectrum-placement task inspired by the social party game Wavelength, in which humans and agents independently place concepts along subjective spectra. We operationalize the Tacit Understanding Index (TUX) as a pairwise measure of similarity between human and agent judgments, and evaluate it with 241 human participants and 200 profile-conditioned LLM agents across four models. We find that nearest human--agent pairs in trait space achieve significantly higher TUX, suggesting that tacit alignment is structured by person-level characteristics rather than random similarity. Regression analyses show that TUX becomes more explainable as predictor sets become richer, with individual traits, decision-making styles, and confidence improving over aggregate trait-distance baselines. These findings suggest that tacit understanding between humans and LLMs is measurable, while revealing the limits of profile-based conditioning for capturing deeper representational alignment.

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

1 major / 0 minor

Summary. The manuscript introduces the Tacit Understanding Index (TUX) as a pairwise similarity metric derived from independent concept placements on subjective spectra in a task inspired by the game Wavelength. With 241 human participants and 200 profile-conditioned LLM agents across four models, it reports that human-agent pairs nearest in trait space achieve significantly higher TUX, indicating that tacit alignment is structured by person-level traits rather than random similarity. Regression analyses further show that TUX becomes more explainable with richer predictor sets (individual traits, decision-making styles, and confidence) over aggregate trait-distance baselines.

Significance. If the results hold, the work supplies a concrete empirical proxy for tacit understanding in human-AI collaboration, showing that individual characteristics shape alignment beyond chance. The study scale (241 humans, 200 agents) and the demonstration that richer predictors improve regression fits constitute clear strengths, offering a foundation for more personalized LLM conditioning. The explicit framing of the task as a proxy and the acknowledgment of profile-conditioning limits add to its utility for the field.

major comments (1)
  1. [Abstract] Abstract: The claim of 'statistically significant differences' in TUX for nearest trait-space pairs provides no information on the exact statistical tests used, multiple-comparison corrections, data exclusion rules, or error bars/effect sizes. This information is load-bearing for evaluating the central empirical result.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their careful review and for identifying the need for greater statistical transparency in the abstract. We address the comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The claim of 'statistically significant differences' in TUX for nearest trait-space pairs provides no information on the exact statistical tests used, multiple-comparison corrections, data exclusion rules, or error bars/effect sizes. This information is load-bearing for evaluating the central empirical result.

    Authors: We agree that the abstract's summary claim would be strengthened by explicit statistical details. The full manuscript describes the tests, corrections, exclusion criteria, and effect sizes in the Methods and Results sections. To make the abstract more self-contained while respecting length constraints, we will revise it in the next version to include a concise statement of the primary test, correction method, and effect size range. revision: yes

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The paper explicitly defines TUX as a pairwise similarity metric on the spectrum-placement task and then reports an empirical observation that nearest trait-space pairs show higher TUX values. This is a statistical comparison of measured quantities, not a quantity forced by the paper's own equations, fitted parameters, or self-citation chains. No load-bearing derivation reduces to its inputs by construction; the central claim remains an independent empirical result against the defined operationalization.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

Review based on abstract only; full paper may contain additional fitted parameters or modeling choices not visible here.

axioms (1)
  • domain assumption Tacit understanding can be operationalized as pairwise similarity between independent human and agent placements on subjective spectra without explicit objectives or feedback.
    This premise directly defines the TUX measure and the experimental task in the abstract.
invented entities (1)
  • TUX (Tacit Understanding Index) no independent evidence
    purpose: Quantify similarity of human and agent judgments on the spectrum-placement task.
    Newly introduced metric; no independent external validation or falsifiable prediction outside the study is described.

pith-pipeline@v0.9.1-grok · 5747 in / 1333 out tokens · 32512 ms · 2026-06-28T21:16:27.567267+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

53 extracted references · 25 canonical work pages · 1 internal anchor

  1. [1]

    Baek and Carolyn Parkinson

    Elisa C. Baek and Carolyn Parkinson. 2022. https://doi.org/10.1111/spc3.12710 Shared understanding and social connection: Integrating approaches from social psychology, social network analysis, and neuroscience . Social and Personality Psychology Compass, 16(11):e12710

    work page doi:10.1111/spc3.12710 2022

  2. [2]

    Gagan Bansal, Besmira Nushi, Ece Kamar, Walter S Lasecki, Daniel S Weld, and Eric Horvitz. 2019. Beyond accuracy: The role of mental models in human-ai team performance. In Proceedings of the AAAI conference on human computation and crowdsourcing, volume 7, pages 2--11

    2019

  3. [3]

    Arnaud Carr \'e , Nicolas Stefaniak, Fanny D'Ambrosio, Le \" la Bensalah, and Chrystel Besche-Richard. 2013. https://doi.org/10.1037/a0032297 The basic empathy scale in adults (bes-a): Factor structure of a revised form . Psychological Assessment, 25(3):679--691

    work page doi:10.1037/a0032297 2013

  4. [4]

    Jiangjie Chen, Xintao Wang, Rui Xu, Siyu Yuan, Yikai Zhang, Wei Shi, Jian Xie, Shuang Li, Ruihan Yang, Tinghui Zhu, Aili Chen, Nianqi Li, Lida Chen, Caiyu Hu, Siye Wu, Scott Ren, Ziquan Fu, and Yanghua Xiao. 2024. https://doi.org/10.48550/arXiv.2404.18231 From persona to personalization: A survey on role-playing language agents . arXiv preprint arXiv:2404.18231

    work page doi:10.48550/arxiv.2404.18231 2024

  5. [5]

    Christiano, Jan Leike, Tom B

    Paul F. Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. In Advances in Neural Information Processing Systems, volume 30

    2017

  6. [6]

    URL https://doi.org/10.1037/10096-006

    Herbert H. Clark and Susan E. Brennan. 1991. https://doi.org/10.1037/10096-006 Grounding in communication . In Lauren B. Resnick, John M. Levine, and Stephanie D. Teasley, editors, Perspectives on Socially Shared Cognition, pages 127--149. American Psychological Association

    work page doi:10.1037/10096-006 1991

  7. [7]

    Curseu, R.J.G

    P.L. Curseu, R.J.G. Jansen, and M.M.H. Chappin. 2013. https://doi.org/10.1371/journal.pone.0056454 Decision rules and group rationality: Cognitive gain or standstill? PLOS ONE, 8(2):e56454

    work page doi:10.1371/journal.pone.0056454 2013

  8. [8]

    Vedant Das Swain and Koustuv Saha. 2024. Teacher, trainer, counsel, spy: how generative ai can bridge or widen the gaps in worker-centric digital phenotyping of wellbeing. In Proceedings of the 3rd Annual Meeting of the Symposium on Human-Computer Interaction for Work, pages 1--13

    2024

  9. [9]

    Vedant Das Swain, Qiuyue" Joy" Zhong, Jash Rajesh Parekh, Yechan Jeon, Roy Zimmermann, Mary P Czerwinski, Jina Suh, Varun Mishra, Koustuv Saha, and Javier Hernandez. 2025. Ai on my shoulder: Supporting emotional labor in front-office roles with an llm-based empathetic coworker. In Proceedings of the 2025 CHI Conference on Human Factors in Computing System...

    2025

  10. [10]

    Xiaoqi Deng, Sarinasadat Hosseini, Yoshihiro Miyake, and Takayuki Nozawa. 2024. https://doi.org/10.3390/bs14110987 Cooperativeness as a personality trait and its impact on cooperative behavior in young east asian adults who synchronized in casual conversations . Behavioral Sciences, 14(11):987

    work page doi:10.3390/bs14110987 2024

  11. [11]

    Weihua Du, Qiushi Lyu, Jiaming Shan, Zhenting Qi, Hongxin Zhang, Sunli Chen, Andi Peng, Tianmin Shu, Kwonjoon Lee, Behzad Dariush, and Chuang Gan. 2024. Constrained human-ai cooperation: An inclusive embodied social intelligence challenge. In Advances in Neural Information Processing Systems, volume 37

    2024

  12. [12]

    Veda Duddu, Jash Rajesh Parekh, Andy Mao, Hanyi Min, Ziang Xiao, Vedant Das Swain, and Koustuv Saha. 2026. Not my truce: Personality differences in ai-mediated workplace negotiation. arXiv preprint arXiv:2604.00464

    arXiv 2026

  13. [13]

    Quentin Ehkirch and Akane Matsumae. 2024. https://doi.org/10.1017/dsj.2024.1 Understanding the influence of interpersonal factors on interactions in co-design through intersubjectivity: A systematic literature review . Design Science, 10:e4

    work page doi:10.1017/dsj.2024.1 2024

  14. [14]

    George Fragiadakis, Christos Diou, George Kousiouris, and Mara Nikolaidou. 2024. Evaluating human-ai collaboration: A review and methodological framework. arXiv preprint arXiv:2407.19098

    arXiv 2024

  15. [15]

    Shane Frederick. 2005. https://doi.org/10.1257/089533005775196732 Cognitive reflection and decision making . Journal of Economic Perspectives, 19(4):25--42

    work page doi:10.1257/089533005775196732 2005

  16. [16]

    Tory Higgins, Maya Rossignac-Milon, and Gerald Echterhoff

    E. Tory Higgins, Maya Rossignac-Milon, and Gerald Echterhoff. 2021. https://doi.org/10.1177/0963721421992027 Shared reality: From sharing-is-believing to merging minds . Current Directions in Psychological Science, 30(2):103--110

    work page doi:10.1177/0963721421992027 2021

  17. [17]

    John and Sanjay Srivastava

    Oliver P. John and Sanjay Srivastava. 1999. The big five trait taxonomy: History, measurement, and theoretical perspectives. In Lawrence A. Pervin and Oliver P. John, editors, Handbook of Personality: Theory and Research, 2 edition, pages 102--138. Guilford Press

    1999

  18. [18]

    Jones and Delroy L

    Daniel N. Jones and Delroy L. Paulhus. 2014. https://doi.org/10.1177/1073191113514105 Introducing the short dark triad (sd3): A brief measure of dark personality traits . Assessment, 21(1):28--41

    work page doi:10.1177/1073191113514105 2014

  19. [19]

    Kahan, Hank Jenkins-Smith, and Donald Braman

    Dan M. Kahan, Hank Jenkins-Smith, and Donald Braman. 2011. https://doi.org/10.1080/13669877.2010.511246 Cultural cognition of scientific consensus . Journal of Risk Research, 14(2):147--174

    work page doi:10.1080/13669877.2010.511246 2011

  20. [20]

    Kichuk and Willi H

    Susan L. Kichuk and Willi H. Wiesner. 1997. https://doi.org/10.1016/S0923-4748(97)00010-6 The big five personality factors and team performance: Implications for selecting successful product design teams . Journal of Engineering and Technology Management, 14(3--4):195--221

    work page doi:10.1016/s0923-4748(97)00010-6 1997

  21. [21]

    Jiwon Kim, Violeta J Rodriguez, Dong Whi Yoo, Eshwar Chandrasekharan, and Koustuv Saha. 2026. Pair-safe: A paired-agent approach for runtime auditing and refining ai-mediated mental health support. arXiv preprint arXiv:2601.12754

    arXiv 2026

  22. [22]

    Sangwook Lee, Adnan Abbas, Yan Chen, Young-Ho Kim, and Sang Won Lee. 2026. Choir: A chatbot-mediated organizational memory leveraging communication in university research labs. In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, pages 1--23

    2026

  23. [23]

    Shunyu Liu, Wenkai Fang, Zetian Hu, Junjie Zhang, Yang Zhou, Kongcheng Zhang, Rongcheng Tu, Ting-En Lin, Fei Huang, Mingli Song, Yongbin Li, and Dacheng Tao. 2025. https://doi.org/10.48550/arXiv.2503.11701 A survey of direct preference optimization . arXiv preprint arXiv:2503.11701

    work page doi:10.48550/arxiv.2503.11701 2025

  24. [24]

    Jennifer Lynch, Alexander McGregor, and Alex J. Benson. 2022. https://doi.org/10.1177/13684302211001944 My way or the highway: Narcissism and dysfunctional team conflict processes . Group Processes & Intergroup Relations, 25(4):1157--1171

    work page doi:10.1177/13684302211001944 2022

  25. [25]

    Dorr, and Francesco Pinto

    Amogh Mannekote, Adam Davies, Guohao Li, Kristy Elizabeth Boyer, ChengXiang Zhai, Bonnie J. Dorr, and Francesco Pinto. 2025. https://doi.org/10.48550/arXiv.2507.02197 Do role-playing agents practice what they preach? belief-behavior consistency in llm-based simulations of human trust . arXiv preprint arXiv:2507.02197

    work page doi:10.48550/arxiv.2507.02197 2025

  26. [26]

    Katelyn Morrison, Zahra Ashktorab, Gabriel Enrique Gonzalez, Djallel Bouneffouf, and Justin Weisz. 2025. Establishing the cooperative game wavelength as a testbed to explore mutual theory of mind. In Proceedings of the Workshop on Advancing AI Through Theory of Mind at AAAI 2025

    2025

  27. [27]

    Sheshera Mysore, Debarati Das, Hancheng Cao, and Bahareh Sarrafzadeh. 2025. Prototypical human-ai collaboration behaviors from llm-assisted writing in the wild. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 16830--16857

    2025

  28. [28]

    Rosemary Pacini and Seymour Epstein. 1999. https://doi.org/10.1037/0022-3514.76.6.972 The relation of rational and experiential information processing styles to personality, basic beliefs, and the ratio-bias phenomenon . Journal of Personality and Social Psychology, 76(6):972--987

    work page doi:10.1037/0022-3514.76.6.972 1999

  29. [29]

    URLhttps://doi.org/10.1145/3586183.3606763

    Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. 2023. https://doi.org/10.1145/3586183.3606763 Generative agents: Interactive simulacra of human behavior . In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1--22

    work page doi:10.1145/3586183.3606763 2023

  30. [30]

    Zou, Jonne Kamphorst, Niles Egan, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Meredith Ringel Morris, Percy Liang, Robb Willer, and Michael S

    Joon Sung Park, Carolyn Q. Zou, Jonne Kamphorst, Niles Egan, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Meredith Ringel Morris, Percy Liang, Robb Willer, and Michael S. Bernstein. 2026. https://arxiv.org/abs/2411.10109 Llm agents grounded in self-reports enable general-purpose simulation of individuals . Preprint, arXiv:2411.10109

    Pith/arXiv arXiv 2026

  31. [31]

    Peeters, Harrie F.J.M

    Miranda A.G. Peeters, Harrie F.J.M. van Tuijl, Christel G. Rutte, and Isabelle Reymen. 2006. https://doi.org/10.1002/per.588 Personality and team performance: a meta analysis . European Journal of Personality, 20(5):377--396

    work page doi:10.1002/per.588 2006

  32. [32]

    Yifu Qiu, Zheng Zhao, Yftah Ziser, Anna Korhonen, Edoardo M Ponti, and Shay B Cohen. 2024. Spectral editing of activations for large language model alignment. Advances in Neural Information Processing Systems, 37:56958--56987

    2024

  33. [33]

    Manning, and Chelsea Finn

    Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. In Advances in Neural Information Processing Systems, volume 36, pages 53728--53741

    2023

  34. [34]

    Beatrice Rammstedt and Oliver P. John. 2007. https://doi.org/10.1016/j.jrp.2006.02.001 Measuring personality in one minute or less: A 10-item short version of the big five inventory in english and german . Journal of Research in Personality, 41(1):203--212

    work page doi:10.1016/j.jrp.2006.02.001 2007

  35. [35]

    Schelling

    Thomas C. Schelling. 1960. The Strategy of Conflict. Harvard University Press

    1960

  36. [36]

    Schmutz, Neal Outland, Sophie Kerstan, Eleni Georganta, and Anna-Sophie Ulfert

    Jan B. Schmutz, Neal Outland, Sophie Kerstan, Eleni Georganta, and Anna-Sophie Ulfert. 2024. https://doi.org/10.1016/j.copsyc.2024.101837 Ai-teaming: Redefining collaboration in the digital era . Current Opinion in Psychology, 58:101837

    work page doi:10.1016/j.copsyc.2024.101837 2024

  37. [37]

    Scott and Reginald A

    Susanne G. Scott and Reginald A. Bruce. 1995. https://doi.org/10.1177/0013164495055005017 Decision-making style: The development and assessment of a new measure . Educational and Psychological Measurement, 55(5):818--831

    work page doi:10.1177/0013164495055005017 1995

  38. [38]

    Julian Senoner, Simon Schallmoser, Bernhard Kratzwald, Stefan Feuerriegel, and Torbj rn Netland. 2024. Explainable ai improves task performance in human--ai collaboration. Scientific reports, 14(1):31150

    2024

  39. [39]

    Soorya Ram Shimgekar, Vipin Gunda, Jiwon Kim, Violeta J Rodriguez, Hari Sundaram, and Koustuv Saha. 2026. Ai psychosis: Does conversational ai amplify delusion-related language? arXiv preprint arXiv:2603.19574

    arXiv 2026

  40. [40]

    Rogerson

    Matthew Sidji, Wally Smith, and Melissa J. Rogerson. 2024. https://doi.org/10.1145/3677081 Human-ai collaboration in cooperative games: A study of playing codenames with an llm assistant . Proceedings of the ACM on Human-Computer Interaction, 8(CHI PLAY):1--25

    work page doi:10.1145/3677081 2024

  41. [41]

    Chandler Smith, Marwa Abdulhai, Manfred Diaz, Marko Tesic, Rakshit Trivedi, Sasha Vezhnevets, Lewis Hammond, Jesse Clifton, Minsuk Chang, Edgar Duenez-Guzman, and 1 others. 2026. Evaluating generalization capabilities of llm-based agents in mixed-motive scenarios using concordia. Advances in neural information processing systems, 38

    2026

  42. [42]

    Kihoon Son, DaEun Choi, Tae Soo Kim, and Juho Kim. 2024. Demystifying tacit knowledge in graphic design: Characteristics, instances, approaches, and guidelines. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, pages 1--18

    2024

  43. [43]

    Yu-Min Tseng, Yu-Chao Huang, Teng-Yun Hsiao, Wei-Lin Chen, Chao-Wei Huang, Yu Meng, and Yun-Nung Chen. 2024. https://doi.org/10.18653/v1/2024.findings-emnlp.969 Two tales of persona in llms: A survey of role-playing and personalization . In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16525--16548

    work page doi:10.18653/v1/2024.findings-emnlp.969 2024

  44. [44]

    Steering Language Models With Activation Engineering

    Alexander Matt Turner, Lisa Thiergart, Gavin Leech, David Udell, Juan J. Vazquez, Ulisse Mini, and Monte MacDiarmid. 2023. https://doi.org/10.48550/arXiv.2308.10248 Steering language models with activation engineering . arXiv preprint arXiv:2308.10248

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2308.10248 2023

  45. [45]

    Gaofeng Wang and Weiwei Hu. 2021. Peer relationships and college students’ cooperative tendencies: Roles of interpersonal trust and social value orientation. Frontiers in Psychology, 12:656412

    2021

  46. [46]

    Qiaosi Wang, Koustuv Saha, Eric Gregori, David Joyner, and Ashok Goel. 2021. Towards mutual theory of mind in human-ai interaction: How language reflects what students perceive about a virtual teaching assistant. In Proceedings of the 2021 CHI conference on human factors in computing systems, pages 1--14

    2021

  47. [47]

    Stanis aw Wo \'z niak, Bart omiej Koptyra, Arkadiusz Janz, Przemys aw Kazienko, and Jan Koco \'n . 2024. Personalized large language models. In 2024 IEEE International Conference on Data Mining Workshops (ICDMW), pages 511--520. IEEE

    2024

  48. [48]

    Guande Wu, Chen Zhao, Claudio Silva, and He He. 2024. Your co-workers matter: Evaluating collaborative capabilities of language models in blocks world. In Findings of the Association for Computational Linguistics: ACL 2024, pages 4941--4957

    2024

  49. [49]

    Jianzhu Yao, Kevin Wang, Ryan Hsieh, Haisu Zhou, Tianqing Zou, Zerui Cheng, Zhangyang Wang, and Pramod Viswanath. 2025. https://doi.org/10.48550/arXiv.2503.12349 Spin-bench: How well do llms plan strategically and reason socially? arXiv preprint arXiv:2503.12349

    work page doi:10.48550/arxiv.2503.12349 2025

  50. [50]

    Dora Zhao, Diyi Yang, and Michael S Bernstein. 2025. Knoll: Creating a knowledge ecosystem for large language models. In Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology, pages 1--23

    2025

  51. [51]

    Huiqi Zou, Pengda Wang, Zihan Yan, Tianjun Sun, and Ziang Xiao. 2025. https://openreview.net/forum?id=xqIwK9mNkj Can LLM ''self-report''?: Evaluating the validity of self-report scales in measuring personality design in LLM -based chatbots . In Second Conference on Language Modeling

    2025

  52. [52]

    online" 'onlinestring :=

    ENTRY address archivePrefix author booktitle chapter edition editor eid eprint eprinttype howpublished institution journal key month note number organization pages publisher school series title type volume year doi pubmed url lastchecked label extra.label sort.label short.list INTEGERS output.state before.all mid.sentence after.sentence after.block STRING...

  53. [53]

    write newline

    " write newline "" before.all 'output.state := FUNCTION n.dashify 't := "" t empty not t #1 #1 substring "-" = t #1 #2 substring "--" = not "--" * t #2 global.max substring 't := t #1 #1 substring "-" = "-" * t #2 global.max substring 't := while if t #1 #1 substring * t #2 global.max substring 't := if while FUNCTION word.in bbl.in capitalize " " * FUNCT...