Too Helpful, Too Harmless, Too Honest or Just Right?
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Dishonesty in Helpful and Harmless Alignment
People tell lies when seeking rewards. Large language models (LLMs) are aligned to human values with reinforcement learning where they get rewards if they satisfy human preference. We find that this also induces dishones…
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrificing helpfulness. We show that frontier LL…
$H^3$Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
Alignment of pretrained LLMs using instruction-based datasets is critical for creating fine-tuned models that reflect human preference. A growing number of alignment-based fine-tuning algorithms and benchmarks emerged re…
Mixture-of-ExpertsOn the Inevitability of Left-Leaning Political Bias in Aligned Language Models
The guiding principle of AI alignment is to train large language models (LLMs) to be harmless, helpful, and honest (HHH). At the same time, there are mounting concerns that LLMs exhibit a left-wing political bias. Yet, t…
Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextualized Urdu Benchmark
Large language models (LLMs) demonstrate strong Helpfulness, Harmlessness, and Honesty (3H) alignment in English-centric settings, but these gains transfer poorly to low-resource languages due to cultural mismatches. Exi…