Effective product development relies on creating a requirements document that defines the product’s technical specifications, yet traditional methods are labor-intensive and depend heavily on expert input. Large language models (LLMs) offer the potential for automation but struggle with limitations in prompt engineering and contextual sensitivity. To overcome these challenges, we developed ReqGPT, a domain-specific LLM fine-tuned on Mistral-7B-Instruct-v0.2 using 107 curated requirements lists. ReqGPT employs a standardized prompt to generate high-quality documents and demonstrated superior performance over GPT-4 and Mistral in multiple criteria based on ISO 29148. Our results underscore ReqGPT’s efficiency, accuracy, cost-effectiveness, and alignment with industry standards, making it an ideal choice for localized use and safeguarding data privacy in technical product development.

The rise of large language models (LLMs) has marked a substantial leap toward artificial general intelligence. However, the utilization of LLMs in (re)insurance sector remains a challenging problem because of the gap between general capabilities and domain-specific requirements. Two prevalent methods for domain specialization of LLMs involve prompt engineering and fine-tuning. In this study, we aim to evaluate the efficacy of LLMs, enhanced with prompt engineering and fine-tuning techniques, on quantitative reasoning tasks within the (re)insurance domain. It is found that (1) compared to prompt engineering, fine-tuning with task-specific calculation dataset provides a remarkable leap in performance, even exceeding the performance of larger pre-trained LLMs; (2) when acquired task-specific calculation data are limited, supplementing LLMs with domain-specific knowledge dataset is an effective alternative; and (3) enhanced reasoning capabilities should be the primary focus for LLMs when tackling quantitative tasks, surpassing mere computational skills. Moreover, the fine-tuned models demonstrate a consistent aptitude for common-sense reasoning and factual knowledge, as evidenced by their performance on public benchmarks. Overall, this study demonstrates the potential of LLMs to be utilized as powerful tools to serve as AI assistants and solve quantitative reasoning tasks in (re)insurance sector.

In the era of digitization and the growing flood of information, the automatic, role-specific identification of information is crucial. This research paper aims to investigate whether the adaptation of LLM is suitable for classifying information obtained from standards for corresponding role profiles. This research reveals that with systematic fine-tuning, prediction accuracy can be increased by almost 100%. The validation was carried out using a two-digit number of standards for three predefined roles and demonstrates the significant potential of LM for labelling content with regard to roles.

This paper describes gft (general fine-tuning), a little language for deep nets, introduced at an ACL-2022 tutorial. gft makes deep nets accessible to a broad audience including non-programmers. It is standard practice in many fields to use statistics packages such as R. One should not need to know how to program in order to fit a regression or classification model and to use the model to make predictions for novel inputs. With gft, fine-tuning and inference are similar to fit and predict in regression and classification. gft demystifies deep nets; no one would suggest that regression-like methods are “intelligent.”

The previous Emerging Trends article (Church et al., 2021. Natural Language Engineering 27(5), 631–645.) introduced deep nets to poets. Poets is an imperfect metaphor, intended as a gesture toward inclusion. The future for deep nets will benefit by reaching out to a broad audience of potential users, including people with little or no programming skills, and little interest in training models. That paper focused on inference, the use of pre-trained models, as is, without fine-tuning. The goal of this paper is to make fine-tuning more accessible to a broader audience. Since fine-tuning is more challenging than inference, the examples in this paper will require modest programming skills, as well as access to a GPU. Fine-tuning starts with a general purpose base (foundation) model and uses a small training set of labeled data to produce a model for a specific downstream application. There are many examples of fine-tuning in natural language processing (question answering (SQuAD) and GLUE benchmark), as well as vision and speech.

The oft-repeated claim that life is ‘written into’ the laws of nature is examined and criticised. Arguments are given in favour of life spreading between near-neighbour planets in rocky impact ejecta (transpermia), but against panspermia, leading to the conclusion that if life is indeed found to be widespread in the universe, some form of life principle or biological determinism must be at work in the process of biogenesis. Criteria for what would constitute a credible life principle are elucidated. I argue that the key property of life is its information content, and speculate that the emergence of the requisite information-processing machinery might require quantum information theory for a satisfactory explanation. Some clues about how decoherence might be evaded are discussed. The implications of some of these ideas for ‘fine-tuning’ are discussed.