@inproceedings{kashyap-etal-2025-helpful,
    title = "Too Helpful, Too Harmless, Too Honest or Just Right?",
    author = "Kashyap, Gautam Siddharth  and
      Dras, Mark  and
      Naseem, Usman",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1510/",
    pages = "29711--29722",
    ISBN = "979-8-89176-332-6",
    abstract = "Large Language Models (LLMs) exhibit strong performance across a wide range of NLP tasks, yet aligning their outputs with the principles of Helpfulness, Harmlessness, and Honesty (HHH) remains a persistent challenge. Existing methods often optimize for individual alignment dimensions in isolation, leading to trade-offs and inconsistent behavior. While Mixture-of-Experts (MoE) architectures offer modularity, they suffer from poorly calibrated routing, limiting their effectiveness in alignment tasks. We propose TrinityX, a modular alignment framework that incorporates a Mixture of Calibrated Experts (MoCaE) within the Transformer architecture. TrinityX leverages separately trained experts for each HHH dimension, integrating their outputs through a calibrated, task-adaptive routing mechanism that combines expert signals into a unified, alignment-aware representation. Extensive experiments on three standard alignment benchmarks{---}Alpaca (Helpfulness), BeaverTails (Harmlessness), and TruthfulQA (Honesty){---}demonstrate that TrinityX outperforms strong baselines, achieving relative improvements of 32.5{\%} in win rate, 33.9{\%} in safety score, and 28.4{\%} in truthfulness. In addition, TrinityX reduces memory usage and inference latency by over 40{\%} compared to prior MoE-based approaches. Ablation studies highlight the importance of calibrated routing, and cross-model evaluations confirm TrinityX{'}s generalization across diverse LLM backbones. Ourcode is available at: https://github.com/gskgautam/TrinityX"
}