Recent large language models often answer factual questions correctly. But users can't trust any given claim a model makes without fact-checking, because language models can hallucinate convincing nonsense. In this work we use reinforcement learning from human preferences (RLHP) to train "open-book" QA models that generate answers whilst also citing specific evidence for their claims, which aids in the appraisal of correctness. Supporting evidence is drawn from multiple documents found via a search engine, or from a single user-provided document. Our 280 billion parameter model, GopherCite, is able to produce answers with high quality supporting evidence and abstain from answering when unsure. We measure the performance of GopherCite by conducting human evaluation of answers to questions in a subset of the NaturalQuestions and ELI5 datasets. The model's response is found to be high-quality 80% of the time on this Natural Questions subset, and 67% of the time on the ELI5 subset. Abstaining from the third of questions for which it is most unsure improves performance to 90% and 80% respectively, approaching human baselines. However, analysis on the adversarial TruthfulQA dataset shows why citation is only one part of an overall strategy for safety and trustworthiness: not all claims supported by evidence are true.
Motivation Gene expression data is commonly used at the intersection of cancer research and machine learning for better understanding of the molecular status of tumour tissue. Deep learning predictive models have been employed for gene expression data due to their ability to scale and remove the need for manual feature engineering. However, gene expression data is often very high dimensional, noisy, and presented with a low number of samples. This poses significant problems for learning algorithms: models often overfit, learn noise, and struggle to capture biologically relevant information. In this article we utilise external biological knowledge embedded within structures of gene interaction graphs such as protein-protein interaction networks (PPI) to guide the construction of predictive models. Results We present GINCCo (Gene Interaction Network Constrained Construction), an unsupervised method for automated construction of computational graph models for gene expression data that are structurally constrained by prior knowledge of gene interaction networks. We employ this methodology in a case study on incorporating a PPI network in cancer phenotype prediction tasks. Our computational graphs are structurally constructed using topological clustering algorithms on the PPI networks which incorporate inductive biases stemming from network biology research on protein complex discovery. Each of the entities in the GINCCo computational graph represent biological entities such as genes, candidate protein complexes and phenotypes instead of arbitrary hidden nodes of a neural network. This provides a biologically relevant mechanism for model regularisation yielding strong predictive performance whilst drastically reducing the number of model parameters and enabling guided post-hoc enrichment analyses of influential gene sets with respect to target phenotypes. Our experiments analysing a variety of cancer phenotypes show that GINCCo often outperform SVM, Fully-Connected MLP, and Randomly-Connected MLPs despite greatly reduced model complexity. Availability https://github.com/paulmorio/gincco contains the source code for our approach. We also release a library with algorithms for protein complex discovery within protein-protein interaction networks at https://github.com/paulmorio/protclus. This repository contains implementations of the clustering algorithms used in this paper.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.