Matching Game Preferences Through Dialogical Large Language Models: A Perspective
Source abstract
Abstract
This perspective paper explores the future potential of “conversational intelligence” by examining how Large Language Models (LLMs) could be combined with GRAPHYP’s network system to better understand human conversations and preferences. Using recent research and case studies, we propose a conceptual framework that could make AI reasoning transparent and traceable, allowing humans to see and understand how AI reaches its conclusions. We present the conceptual perspective of “Matching Game Preferences through Dialogical Large Language Models (D-LLMs),” a proposed system that would allow multiple users to share their different preferences through structured conversations. This approach envisions personalizing LLMs by embedding individual user preferences directly into how the model makes decisions. The proposed D-LLM framework would require three main components: (1) reasoning processes that could analyze different search experiences and guide performance, (2) classification systems that would identify user preference patterns, and (3) dialogue approaches that could help humans resolve conflicting information. This perspective framework aims to create an interpretable AI system where users could examine, understand, and combine the different human preferences that influence AI responses, detected through GRAPHYP’s search experience networks. The goal of this perspective is to envision AI systems that would not only provide answers but also show users how those answers were reached, making artificial intelligence more transparent and trustworthy for human decision-making.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Language and cultural evolution · Misinformation and Its Impacts
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Dionysian Economics Laboratory (LED), Université Paris 8, 93200 Saint-Denis, France
Université Paris Sciences et Lettres (PSL), 75006 Paris, France
Aix Marseille University, CNRS, LIS, 13007 Marseille, France
References (63)
Show source-provided references
1. Human Evaluation of Procedural Knowledge Graph Extraction from Text with Large Language Models
2. Zhao, J., Zhuo, L., Shen, Y., Qu, M., Liu, K., Bronstein, M., Zhu, Z., and Tang, J. (2023). Epistemic GraphText: Graph Reasoning in Text Space. arXiv.
3. Zhang, Z., Rossi, R.A., Kveton, B., Shao, Y., Yang, D., Zamani, H., Dernoncourt, F., Barrow, J., Yu, T., and Kim, S. (2025). Personalization of Large Language Models: A Survey. arXiv.
4. Artificial intelligence and illusions of understanding in scientific research10.1038/s41586-024-07146-0 ↗
5. Shojaee, P., Mirzadeh, I., Alizadeh, K., Horton, M., Bengio, S., and Farajtabar, M. (2025). The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity. arXiv.
6. Shaikh, O., Lam, M.S., Hejna, J., Shao, Y., Cho, H., Bernstein, M.S., and Yang, D. (2024). Aligning Language Models with Demonstrated Feedback. arXiv.
7. Chollet, F. (2019). On the Measure of Intelligence. arXiv.
8. When large language models meet personalization: Perspectives of challenges and opportunities10.1007/s11280-024-01276-1 ↗
9. Human-in-the-Loop Integration with Domain-Knowledge Graphs for Explainable Federated Deep Learning
10. Assessing LLMs Suitability for Knowledge Graph Completion10.1007/978-3-031-71170-1_22 ↗
11. Qiu, Z., Luo, L., Pan, S., and Liew, A.W. (2024). Unveiling User Preferences: A Knowledge Graph and LLM-Driven Approach for Conversational Recommendation. arXiv.
12. Bai, Y., Jones, A., Ndousse, K., Askell, A., Chen, A., Dassarma, N., Drain, D., Fort, S., Ganguli, D., and Henighan, T.J. (2022). Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. arXiv.
13. Zhu, S., and Sun, S. (2024). A short survey: Exploring knowledge graph-based neural-symbolic system from application perspective. arXiv.
14. A Very Brief Introduction to Machine Learning with Applications to Communication Systems10.1109/TCCN.2018.2881442 ↗
15. Fabre, R., Azeroual, O., Bellot, P., Schöpfel, J., and Egret, D. (2022). Retrieving Adversarial Cliques in Cognitive Communities: A New Conceptual Framework for Scientific Knowledge Graphs. Future Internet, 14.10.3390/fi14090262 ↗
16. Fabre, R., Azeroual, O., Schöpfel, J., Bellot, P., and Egret, D. (2023). A Multiverse Graph to Help Scientific Reasoning from Web Usage: Interpretable Patterns of Assessor Shifts in GRAPHYP. Future Internet, 15.10.3390/fi15040147 ↗
17. Fabre, R., Bellot, P., and Egret, D. (2025). Challenging Scientific Categorizations Through Dispute Learning. Appl. Sci., 15.10.3390/app15042241 ↗
18. Jiang, L., Wu, X., Huang, S., Dong, Q., Chi, Z., Dong, L., Zhang, X., Lv, T., Cui, L., and Wei, F. (2025). Think Only When You Need with Large Hybrid-Reasoning Models. arXiv.
19. O’Keefe, C., Ramakrishnan, K., Tay, J., and Winter, C. (2025). Law-Following AI: Designing AI Agents to Obey Human Laws. Fordham Law Rev., 94, Available online: https://law-ai.org/law-following-ai/.10.2139/ssrn.5242643 ↗
20. The benefits and dangers of anthropomorphic conversational agents10.1073/pnas.2415898122 ↗
21. Tan, Z., and Jiang, M. (2023). User Modeling in the Era of Large Language Models: Current Research and Future Directions. arXiv.
22. Kuusela, O. (2019). The Method of Language-Games as a Method of Logic. Wittgenstein on Logic as the Method of Philosophy: Re-Examining the Roots and Development of Analytic Philosophy, Oxford Academic. [Online ed.].10.1093/oso/9780198829751.001.0001 ↗
23. Clark, N., Shen, H., Howe, W., and Mitra, T. (2025). Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery. arXiv.
24. An Introduction to Variational Methods for Graphical Models10.1007/978-94-011-5014-9_5 ↗
25. The pivot penalty in research10.1038/s41586-025-09048-1 ↗
26. Jiang, P., Rayan, J., Dow, S.P., and Xia, H. (November, January 29). Graphologue: Exploring Large Language Model Responses with Interactive Diagrams. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (UIST ‘23), San Francisco, CA, USA.
27. Tang, C., Zhang, H., Loakman, T., Lin, C., and Guerin, F. (2023). Enhancing Dialogue Generation via Dynamic Graph Knowledge Aggregation. arXiv.10.18653/v1/2023.acl-long.253 ↗
28. Building knowledge-grounded dialogue systems with graph-based semantic modelling10.1016/j.knosys.2024.111943 ↗
29. Lin, Y., Chen, Q., Cheng, Y., Zhang, J., Liu, Y., Hsia, L., and Chen, Y. (2025). LLM Inference Enhanced by External Knowledge: A Survey. arXiv.
30. Khorashadizadeh, H., Zahra Amara, F., Ezzabady, M., Ieng, F., Tiwari, S., Mihindukulasooriya, N., Groppe, J., Sahri, S., Benamara, F., and Groppe, S. (2024). Research Trends for the Interplay between Large Language Models and Knowledge Graphs. arXiv.
31. Kumar, R., Ishan, K., Kumar, H., and Singla, A. (2025). LLM-Powered Knowledge Graphs for Enterprise Intelligence and Analytics. arXiv.
32. Challenging Machines to the Language Game: Wittgensteinian Philosophy and Future Dimensions of Artificial Intelligence10.1007/s40647-015-0085-8 ↗
33. Philosophical Investigations into AI Alignment: A Wittgensteinian Framework
34. Van Gennep, A. (2025, June 20). Essai d’une Théorie des Langues Spéciales. Available online: https://elianedaphy.org/IMG/pdf/VanGennep_1908_LanguesSpeciales.pdf.
35. Markowitz, E., Ramakrishna, A., Dhamala, J., Mehrabi, N., Peris, C., Gupta, R., Chang, K., and Galstyan, A. (2024, January 11–16). Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Black-box Language Models with Knowledge Graphs. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Bangkok, Thailand. Available online: https://aclanthology.org/2024.acl-long.665/.10.18653/v1/2024.acl-long.665 ↗
36. Li, Q., Huang, C., Li, S., Xiang, Y., Xiong, D., and Lei, W. (2025, January 19–24). GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering. Proceedings of the 31st International Conference on Computational Linguistics, Abu Dhabi, United Arab Emirates.
37. Cao, L. (2024, January 11–16). GraphReason: Enhancing Reasoning Capabilities of Large Language Models through A Graph-Based Verification Approach. Proceedings of the 2nd Workshop on Natural Language Reasoning and Structured Explanations, Bangkok, Thailand. Available online: https://aclanthology.org/2024.nlrse-1.1/.10.18653/v1/2024.nlrse-1.1 ↗
38. Zhu, Z., Huang, T., Wang, K., Ye, J., Chen, X., and Luo, S. (2025). Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey. arXiv.
39. Bougzime, O., Jabbar, S., Cruz, C., and Demoly, F. (2025). Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations. arXiv.
40. Besta, M., Memedi, F., Zhang, Z., Gerstenberger, R., Piao, G., Blach, N., Nyczyk, P., Copik, M., Kwaśniewski, G., and Muller, J. (2024). Demystifying Chains, Trees, and Graphs of Thoughts. arXiv.
41. Zhu, Y., Wang, X., Chen, J., Qiao, S., Ou, Y., Yao, Y., Deng, S., Chen, H., and Zhang, N. (2023). LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities. arXiv.10.1007/s11280-024-01297-w ↗
42. Ribeiro, L.C., Bernardes, A.T., and Mello, H. (2023). On the fractal patterns of language structures. PLoS ONE, 18.10.1371/journal.pone.0285630 ↗
43. Alabdulmohsin, I., Tran, V.Q., and Dehghani, M. (2024). Fractal Patterns May Illuminate the Success of Next-Token Prediction. arXiv.
44. Shen, X., Wang, F., and Xia, R. (2025). Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQA. arXiv.
45. Tan, X., Wang, X., Liu, Q., Xu, X., Yuan, X., Zhu, L., and Zhang, W. (2025). Hydra: Structured Cross-Source Enhanced Large Language Model Reasoning. arXiv.
46. Yuan, Y., Liu, C., Yuan, J., Sun, G., Li, S., and Zhang, M. (2024). A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning. arXiv.
47. Hare, R., Patel, N., Tang, Y., and Patel, P. (2022, January 12–15). A Graph-based Approach for Adaptive Serious Games. Proceedings of the IEEE Intl Conference on Dependable, Autonomic and Secure Computing, International Conference on Pervasive Intelligence and Computing, International Conference on Cloud and Big Data Computing, International Conference on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), Falerna, Italy.10.1109/DASC/PiCom/CBDCom/Cy55231.2022.9928013 ↗
48. Efficient Algorithms for Personalized PageRank Computation: A Survey10.1109/TKDE.2024.3376000 ↗
49. Trevisan, A. (2024). The BS-meter: A ChatGPT-Trained Instrument to Detect Sloppy Language-Games. arXiv.
50. Coppolillo, E. (2025). Injecting Knowledge Graphs into Large Language Models. arXiv.
51. Leandro, J., Rao, S., Xu, M., Xu, W., Jojic, N., Brockett, C., and Dolan, B. (2024, January 5–8). GENEVA: GENErating and Visualizing branching narratives using LLMs. Proceedings of the 2024 IEEE Conference on Games (CoG), Milan, Italy.10.1109/CoG60054.2024.10645625 ↗
52. Au, S., Dimacali, C.J., Pedirappagari, O., Park, N., Dernoncourt, F., Wang, Y., Kanakaris, N., Deilamsalehy, H., Rossi, R.A., and Ahmed, N.K. (2025). Personalized Graph-Based Retrieval for Large Language Models. arXiv.
53. Gunawan, A., Ruan, J., and Huang, X. (August, January 31). A Graph Neural Network Reasoner for Game Description Language. Proceedings of the 19th International Conference on Principles of Knowledge Representation and Reasoning—Special Session on KR and Machine Learning, Haifa, Israel.
54. Integrating Graphs with Large Language Models: Methods and Prospects10.1109/MIS.2023.3332242 ↗
55. Zhang, M., Sun, M., Wang, P., Fan, S., Mo, Y., Xu, X., Liu, H., Yang, C., and Shi, C. (2024, January 13–17). GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks. Proceedings of the ACM Web Conference 2024 (WWW ‘24), Singapore.10.1145/3589334.3645682 ↗
56. Chen, S., Zhao, Z., Zhao, Y., and Li, X. (2024). Apollonion: Profile-centric Dialog Agent. arXiv.
57. Wu, S., Fung, M., Qian, C., Kim, J., Hakkani-Tur, D., and Ji, H. (2024). Aligning LLMs with Individual Preferences via Interaction. arXiv.
58. Kau, A., He, X., Nambissan, A., Astudillo, A., Yin, H., and Aryani, A. (2024). Combining Knowledge Graphs and Large Language Models. arXiv.10.59350/mk9dg-4r198 ↗
59. Guo, Y., Guo, M., Su, J., Yang, Z., Zhu, M., Li, H., Qiu, M., and Liu, S.S. (2024). Bias in Large Language Models: Origin, Evaluation, and Mitigation. arXiv.
60. Ibáñez, L.-D., Domingue, J., Kirrane, S., Seneviratne, O., Third, A., and Vidal, M.-E. (2023). Trust, Accountability, and Autonomy in Knowledge Graph-based AI for Self-determination. arXiv.
61. Zhao, X., Blum, M., Yang, R., Yang, B., Márquez Carpintero, L., Pina-Navarro, M., Wang, T., Li, X., Li, H., and Fu, Y. (2024). AGENTiGraph: An Interactive Knowledge Graph Platform for LLM-based Chatbots Utilizing Private Data. arXiv.
62. Garello, L., Belgiovine, G., Russo, G., Rea, F., and Sciutti, A. (2025). Building Knowledge from Interactions: An LLM-Based Architecture for Adaptive Tutoring and Social Reasoning. arXiv.
63. Yu, W., Tang, S., Huang, Y., Dong, N., Fan, L., Qi, H., Liu, W., Diao, X., Chen, X., and Ouyang, W. (2025). Dynamic Knowledge Exchange and Dual-diversity Review: Concisely Unleashing the Potential of a Multi-Agent Research Team. arXiv.