paper-with-me

Papers

A bi-objective $ε$-constrained framework for quality-cost optimization in language model ensembles

2023-12-26 · Aditi Singla, Aditya Singh, Kanishk Kukreja

We propose an ensembling framework that uses diverse open-sourced Large Language Models (LLMs) to achieve high response quality while maintaining cost efficiency. We formulate a bi-objective optimization problem to represent the quality-cost tradeoff and then introduce an additional budget constraint that reduces the problem to a straightforward 0/1 knapsack problem. We empirically demonstrate that our framework outperforms the existing ensembling approaches in response quality while significantly reducing costs.

📄 PDF Abstract BibTeX arXiv:2312.16119

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Automated Computational Energy Minimization of ML Algorithms using Constrained Bayesian Optimization

2024-07-08 · Pallavi Mitra, Felix Biessmann

Bayesian optimization (BO) is an efficient framework for optimization of black-box objectives when function evaluations are costly and gradient information is not easily accessible. BO has been successfully applied to au…

Bayesian OptimizationHyperparameter Optimization

Momentum-constrained Hybrid Heuristic Trajectory Optimization Framework with Residual-enhanced DRL for Visually Impaired Scenarios

2026-04-16 · Yuting Zeng, Zhiwen Zheng, Jingya Wang, You Zhou 외 arxiv

Safe and efficient assistive planning for visually impaired scenarios remains challenging, since existing methods struggle with multi-objective optimization, generalization, and interpretability. In response, this paper …

Reinforcement Learning

Constrained Stein Variational Trajectory Optimization

2023-08-23 · Thomas Power, Dmitry Berenson

We present Constrained Stein Variational Trajectory Optimization (CSVTO), an algorithm for performing trajectory optimization with constraints on a set of trajectories in parallel. We frame constrained trajectory optimiz…

Runtime Analysis of Single- and Multi-Objective Evolutionary Algorithms for Chance Constrained Optimization Problems with Normally Distributed Random Variables

2021-09-13 · Frank Neumann, Carsten Witt

Chance constrained optimization problems allow to model problems where constraints involving stochastic components should only be violated with a small probability. Evolutionary algorithms have been applied to this scena…

Evolutionary Algorithms

Towards NSFW-Free Text-to-Image Generation via Safety-Constraint Direct Preference Optimization

2025-04-19 · Shouwei Ruan, Zhenyu Wu, Yao Huang, Ruochen Zhang 외

Ensuring the safety of generated content remains a fundamental challenge for Text-to-Image (T2I) generation. Existing studies either fail to guarantee complete safety under potentially harmful concepts or struggle to bal…

Contrastive LearningImage GenerationSafety AlignmentText to Image Generation+1