๐
๐
Old Age
Evolutionary Soups: Evolving Mixture-of-Experts for Multi-Objective LLM Alignment
August 30, 2026 ยท Grace Period ยท ๐ EMNLP 2026
Authors
Lingxiao Kong, Steffen Staab, Cong Yang, Oya Beyan, Zeyd Boukhers
arXiv ID
2608.29978
Category
cs.CL: Computation & Language
Cross-listed
cs.LG,
cs.NE
Citations
0
Venue
EMNLP 2026
Abstract
Large language models are increasingly required to generate responses that satisfy multiple competing objectives. Since optimal trade-offs depend on both user preferences and input prompts, controllable multi-objective generation must dynamically adapt models at inference time without retraining. To address this, we propose Evolutionary Soups, a mixture-of-experts framework for fine-grained generation control, with gating networks trained via an evolutionary algorithm. The per-layer gating networks dynamically produce expert-merging coefficients from hidden-state representations, while the evolutionary algorithm incorporates greedy hypervolume contribution for effective evolution of these gating networks, achieving consistent improvements on large and noisy training datasets and broader coverage of the non-convex Pareto front. Experiments across three tasks demonstrate the effectiveness of Evolutionary Soups over baselines: it achieves the best hypervolume, linear utility, and Tchebyshev utility (~20% improvement) among controllable methods on all tasks.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computation & Language
๐
๐
Old Age
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
๐
๐
Old Age
XLNet: Generalized Autoregressive Pretraining for Language Understanding
๐ฎ
๐ฎ
The Ethereal
Effective Approaches to Attention-based Neural Machine Translation
๐
๐
Old Age
A large annotated corpus for learning natural language inference
๐
๐
Old Age