Fine-Tuning Large Enterprise Language Models via Ontological Reasoning

Baldazzi, Teodoro; Bellomarini, Luigi; Ceri, Stefano; Colombo, Andrea; Gentili, Andrea; Sallinger, Emanuel

doi:10.1007/978-3-031-45072-3_6

Cited by 9 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the notable successes of LLMs, their performance significantly deteriorates in low-resource settings, particularly for domain-specific environments where the data available for training is very scarce (for instance, in the case of emerging events like novel viruses) or, in certain cases, completely unavailable (such as in privacy-sensitive enterprise contexts) (Ling et al, 2023;Chen et al, 2023b;Baldazzi et al, 2023). Further, they are less likely to be trained with ones similar to these specialized data, leading to constrained capability in handling them.…”

Section: Data Augmentationmentioning

confidence: 99%

Measuring Phylogenetic Information of Incomplete Sequence Data

2021

View full text Add to dashboard Cite

Widely used approaches for extracting phylogenetic information from aligned sets of molecular sequences rely upon probabilistic models of nucleotide substitution or amino-acid replacement. The phylogenetic information that can be extracted depends on the number of columns in the sequence alignment and will be decreased when the alignment contains gaps due to insertion or deletion events. Motivated by the measurement of information loss, we suggest assessment of the Effective Sequence Length (ESL) of an aligned data set. The ESL can differ from the actual number of columns in a sequence alignment because of the presence of alignment gaps. Furthermore, the estimation of phylogenetic information is affected by model misspecification. Inevitably, the actual process of molecular evolution differs from the probabilistic models employed to describe this process. This disparity means the amount of phylogenetic information in an actual sequence alignment will differ from the amount in a simulated data set of equal size, which motivated us to develop a new test for model adequacy. Via theory and empirical data analysis, we show how to disentangle the effects of gaps and model misspecification. By comparing the Fisher information of actual and simulated sequences, we identify which alignment sites and tree branches are most affected by gaps and model misspecification.

show abstract

Section: Data Augmentationmentioning

confidence: 99%