HEIMAT debiases language models by generating heuristic prompts, building substitution sets, and fine-tuning the model with a Jensen-Shannon divergence loss to align predictions across demographic groups, with no fixed preference datasets.
KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
As scaling large language models faces prohibitive costs, multi-agent systems emerge as a promising alternative, though challenged by static knowledge assumptions and coordination inefficiencies. We introduces Knowledge-Aware Bayesian Bandits (KABB), a novel framework that enhances multi-agent system coordination through semantic understanding and dynamic adaptation. The framework features three key innovations: a three-dimensional knowledge distance model for deep semantic understanding, a dual-adaptation mechanism for continuous expert optimization, and a knowledge-aware Thompson Sampling strategy for efficient expert selection. Extensive evaluation demonstrates KABB achieves an optimal cost-performance balance, maintaining high performance while keeping computational demands relatively low in multi-agent coordination.
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Heuristic Perspective on Debiasing Language Models
HEIMAT debiases language models by generating heuristic prompts, building substitution sets, and fine-tuning the model with a Jensen-Shannon divergence loss to align predictions across demographic groups, with no fixed preference datasets.