{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T18:15:17Z","timestamp":1783707317716,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"VAIshwik BHArtiya Vaigyanik (VAIBHAV) Fellowship, DST, Government of India.","award":["INAE\/DST\/VF\/2024\/II\/03"],"award-info":[{"award-number":["INAE\/DST\/VF\/2024\/II\/03"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,13]]},"DOI":"10.1145\/3795095.3805132","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T17:44:29Z","timestamp":1783705469000},"page":"271-279","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Objective Orchestration of Small Language Model Ensembles: Balancing Accuracy, Diversity, and Fairness"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2212-6023","authenticated-orcid":false,"given":"Advay","family":"Dhar","sequence":"first","affiliation":[{"name":"Department of Computer Science And Engineering, Jadavpur Unversity, Kolkata, West Bengal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6843-4508","authenticated-orcid":false,"given":"Swagatam","family":"Das","sequence":"additional","affiliation":[{"name":"Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, West Bengal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7402-9939","authenticated-orcid":false,"given":"Kalyanmoy","family":"Deb","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, Michigan, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"J. Baumann and O. Kramer. 2024. Evolutionary multi-objective optimization of large language model prompts for balancing sentiments. arXiv:2401.09862. Available: https:\/\/arxiv.org\/abs\/2401.09862.","DOI":"10.1007\/978-3-031-56855-8_13"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. 610\u2013623","author":"Bender E. M.","unstructured":"E. M. Bender, T. Gebru, A. McMillan-Major, and S. Shmitchell. 2021. On the dangers of stochastic parrots: Can language models be too big?. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. 610\u2013623."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990567"},{"key":"e_1_3_2_1_4_1","unstructured":"T. Bolukbasi K.-W. Chang J. Zou V. Saligrama and A. Kalai. 2016. Man is to computer programmer as woman is to homemaker? Debiasing word embeddings. In Advances in Neural Information Processing Systems. 4349\u20134357."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_2_1_6_1","unstructured":"Lingjiao Chen Matei Zaharia and James Zou. 2023. FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance. arXiv:2305.05176 [cs.LG] https:\/\/arxiv.org\/abs\/2305.05176"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2013.2281535"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"e_1_3_2_1_9_1","unstructured":"\"Hugging Face\". 2026. Career Guidance Counsellor QA Dataset. Hugging Face Datasets. https:\/\/huggingface.co\/datasets\/advy\/career-guidance-counsellor-QA"},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus W.","year":"2022","unstructured":"W. Fedus, B. Zoph, and N. Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research 23 (2022), 1\u201339.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_11_1","unstructured":"M. Fouda et al. 2025. Benchmarking LLMs in mental health with MentalBench.OpenReview \/ arXiv technical report. Available: https:\/\/openreview.net\/."},{"key":"e_1_3_2_1_12_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan Amy Yang Angela Fan Anirudh Goyal et al. 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_13_1","unstructured":"Q. Guo R. Wang J. Guo B. Li K. Song X. Tan G. Liu J. Bian and Y. Yang. 2023. Connecting large language models with evolutionary algorithms yields powerful prompt optimizers (EvoPrompt). arXiv:2309.08532. Available: https:\/\/arxiv.org\/abs\/2309.08532."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Z. Guo et al. 2024. Large language models for mental health applications: A systematic review. Systematic review. PubMed: PMID entry (2024).","DOI":"10.2196\/preprints.57400"},{"key":"e_1_3_2_1_15_1","volume-title":"Tung Dao, Dao Tran, and Huynh Thi Thanh Binh.","author":"Ha Minh Hieu","year":"2026","unstructured":"Minh Hieu Ha, Hung Phan, Tung Duy Doan, Tung Dao, Dao Tran, and Huynh Thi Thanh Binh. 2026. Pareto-Grid-Guided Large Language Models for Fast and High-Quality Heuristics Design in Multi-Objective Combinatorial Optimization. arXiv:2507.20923 [cs.NE] https:\/\/arxiv.org\/abs\/2507.20923 GECCO 2025."},{"key":"e_1_3_2_1_16_1","unstructured":"L. Hanu and Unitary team. 2020. Detoxify. GitHub repository: https:\/\/github.com\/unitaryai\/detoxify."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770\u2013778","author":"He K.","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770\u2013778."},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Evolutionary Multi-Criterion Optimization. 64\u201378","author":"Horn D.","unstructured":"D. Horn, T. Wagner, D. Biermann, C. Weihs, and B. Bischl. 2015. Model-based multi-objective optimization: Taxonomy, multi-point proposal, toolbox and benchmark. In International Conference on Evolutionary Multi-Criterion Optimization. 64\u201378."},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Learning Representations.","author":"Hu E. J.","year":"2022","unstructured":"E. J. Hu et al. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L\u00e9lio Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2023. Mistral 7B. arXiv:2310.06825 [cs.CL] https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"e_1_3_2_1_21_1","unstructured":"Dongfu Jiang Xiang Ren and Bill Yuchen Lin. 2023. LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion. arXiv:2306.02561 [cs.CL] https:\/\/arxiv.org\/abs\/2306.02561"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Y. Jinnai. 2025. Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport. arXiv:2505.23078.","DOI":"10.18653\/v1\/2025.acl-long.1370"},{"key":"e_1_3_2_1_23_1","unstructured":"D. Kraft. 1988. A software package for sequential quadratic programming. Technical Report DFVLR-FB 88-28. DLR German Aerospace Center."},{"key":"e_1_3_2_1_24_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"31","author":"Li Hao","year":"2018","unstructured":"Hao Li, Zheng Xu, Gavin Taylor, and Tom Goldstein. 2018. Visualizing the Loss Landscape of Neural Nets. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 31. https:\/\/papers.nips.cc\/paper_files\/paper\/2018\/hash\/09a511a6912975dabe1f16f62f2228c9-Abstract.html"},{"key":"e_1_3_2_1_25_1","unstructured":"Jiwei Li Michel Galley Chris Brockett Jianfeng Gao and Bill Dolan. 2016. A Diversity-Promoting Objective Function for Neural Conversation Models. arXiv:1510.03055 [cs.CL] https:\/\/arxiv.org\/abs\/1510.03055"},{"key":"e_1_3_2_1_26_1","volume-title":"Text Summarization Branches Out: Proceedings of the ACL-04 Workshop. 74\u201381","author":"Lin C.-Y.","year":"2004","unstructured":"C.-Y. Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out: Proceedings of the ACL-04 Workshop. 74\u201381."},{"key":"e_1_3_2_1_27_1","volume-title":"European Conference on Computer Vision. 35\u201351","author":"Z. Lu","year":"2020","unstructured":"Z. Lu et al. 2020. NSGANetV2: Evolutionary multi-objective surrogate-assisted neural architecture search. In European Conference on Computer Vision. 35\u201351."},{"key":"e_1_3_2_1_28_1","unstructured":"Sebastien Bubeck Caio C\u00e9sar Teodoro Mendes Weizhu Chen Allie Del Giorno Ronen Eldan Sivakanth Gopi Suriya Gunasekar Mojan Javaheripi Piero Kauffmann Yin Tat Lee Yuanzhi Li Anh Nguyen Gustavo de Rosa Olli Saarikivi Adil Salim Shital Shah Michael Santacroce Harkirat Singh Behl Adam Taumann Kalai Xin Wang Rachel Ward Philipp Witte Cyril Zhang Yi Zhang Marah Abdin Jyoti Aneja. 2023. Phi-2: The surprising power of small language models. https:\/\/www.microsoft.com\/en-us\/research\/blog\/phi-2-the-surprising-power-of-small-language-models\/"},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Machine Learning. 6755\u20136764","author":"Mart\u00ednez N.","unstructured":"N. Mart\u00ednez, M. Bertran, and G. Sapiro. 2020. Minimax Pareto fairness: A multi-objective perspective. In International Conference on Machine Learning. 6755\u20136764."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311\u2013318","author":"Papineni K.","year":"2002","unstructured":"K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu. 2002. BLEU: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311\u2013318."},{"key":"e_1_3_2_1_31_1","unstructured":"Qwen Team A. Yang et al. 2024. Qwen2: A family of open large language models (technical report). arXiv:2407.10671. Available: https:\/\/arxiv.org\/abs\/2407.10671."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. 3982\u20133992","author":"Reimers N.","unstructured":"N. Reimers and I. Gurevych. 2019. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. 3982\u20133992."},{"key":"e_1_3_2_1_33_1","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2020. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. arXiv:1910.01108 [cs.CL] https:\/\/arxiv.org\/abs\/1910.01108"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"R. E. Schapire. 2003. The boosting approach to machine learning: An overview. In Nonlinear Estimation and Classification. 149\u2013171.","DOI":"10.1007\/978-0-387-21579-2_9"},{"key":"e_1_3_2_1_35_1","volume-title":"International Conference on Learning Representations.","author":"N. Shazeer","year":"2017","unstructured":"N. Shazeer et al. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_36_1","unstructured":"X. Shen et al. 2025. MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance. arXiv preprint arXiv:2503.13509v1."},{"key":"e_1_3_2_1_37_1","volume-title":"Stanford Alpaca: An instruction-following LLaMA model","author":"Taori R.","year":"2023","unstructured":"R. Taori, I. Gulrajani, T. Zhang, Y. Dubois, X. Li, C. Guestrin, P. Liang, and T. B. Hashimoto. 2023. Stanford Alpaca: An instruction-following LLaMA model. Stanford Center for Research on Foundation Models (CRFM) blog and GitHub release. Available: https:\/\/crfm.stanford.edu\/2023\/03\/13\/alpaca.html and https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_2_1_38_1","volume-title":"Cassidy Hardin, Surya Bhupatiraju, L\u00e9onard Hussenot, et al.","author":"Team Gemma","year":"2024","unstructured":"Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, L\u00e9onard Hussenot, et al. 2024. Gemma 2: Improving Open Language Models at a Practical Size. arXiv:2408.00118 [cs.CL] https:\/\/arxiv.org\/abs\/2408.00118"},{"key":"e_1_3_2_1_39_1","volume-title":"Mixture-of-Agents Enhances Large Language Model Capabilities. In ICLR","author":"Wang J.","year":"2025","unstructured":"J. Wang, J. Wang, B. Athiwaratkun, C. Zhang, and J. Zou. 2025. Mixture-of-Agents Enhances Large Language Model Capabilities. In ICLR 2025. arXiv preprint arXiv:2406.04692. Available: https:\/\/arxiv.org\/abs\/2406.04692."},{"key":"e_1_3_2_1_40_1","unstructured":"Peiyuan Zhang Guangtao Zeng Tianduo Wang and Wei Lu. 2024. TinyLlama: An Open-Source Small Language Model. arXiv:2401.02385 [cs.CL] https:\/\/arxiv.org\/abs\/2401.02385"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2003"}],"event":{"name":"GECCO '26: Genetic and Evolutionary Computation Conference","location":"Centro Internacional de Convenciones CIC-ANDE San Jose Costa Rica","acronym":"GECCO '26","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"]},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3795095.3805132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T17:46:58Z","timestamp":1783705618000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3795095.3805132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":41,"alternative-id":["10.1145\/3795095.3805132","10.1145\/3795095"],"URL":"https:\/\/doi.org\/10.1145\/3795095.3805132","relation":{},"subject":[],"published":{"date-parts":[[2026,7,10]]},"assertion":[{"value":"2026-07-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}