Large Language Models (LLMs) have displayed remarkable capabilities across diverse domains, but their training remains resource – and time-intensive, requiring massive computational resources and careful orchestration of training procedures. Model souping – the practice of averaging weights from multiple models of the same architecture – has emerged as a promising pre- and post-training technique that can enhance performance without expensive retraining. We observe that previous souping approaches can lead to collapse in precision-sensitive LLM capabilities. In this paper, we introduce Soup of Category Experts (SoCE), a principled approach for model souping to overcome this shortcoming. The proposed method utilizes benchmark composition to identify optimal model candidates and applies non-uniform weighted averaging to maximize performance. Contrary to previous approaches, our method leverages the observation that different clusters (or categories) of points within a benchmark often exhibit low inter-correlations in model performance. SoCE identifies "expert" models for each weakly-correlated category cluster and combines them using optimized weighted averaging rather than uniform weights. We demonstrate that SoCE improves performance and robustness across multiple domains achieves state-of-the-art results on the Berkeley Function Calling Leaderboard.

The input vocabulary and the representations learned are crucial to the performance of neural NLP models. Using the full vocabulary results in less explainable and more memory intensive models, with the embedding layer often constituting the majority of model parameters. It is thus common to use a smaller vocabulary to lower memory requirements and construct more interpertable models. We propose a vocabulary selection method that views words as members of a team trying to maximize the model’s performance. We apply power indices from cooperative game theory, including the Shapley value and Banzhaf index, that measure the relative importance of individual team members in accomplishing a joint task. We approximately compute these indices to identify the most influential words. Our empirical evaluation examines multiple NLP tasks, including sentence and document classification, question answering and textual entailment. We compare to baselines that select words based on frequency, TF-IDF and regression coefficients under L1 regularization, and show that this game-theoretic vocabulary selection outperforms all baseline on a range of different tasks and datasets.

We present a new architecture for named entity recognition. Our model employs multiple independent bidirectional LSTM units across the same input and promotes diversity among them by employing an inter-model regularization term. By distributing computation across multiple smaller LSTMs we find a significant reduction in the total number of parameters. We find our architecture achieves state-of-the-art performance on the CoNLL 2003 NER dataset.