As the cultural heritage sector increasingly adopts technologies like Retrieval-Augmented Generation (RAG) to provide more personalised search experiences and enable conversations with collections data, the demand for specialised evaluation datasets has grown. While end-to-end system testing is essential, it’s equally important to assess individual components. We target the final, answering task, which is well-suited to Machine Reading Comprehension (MRC). Although existing MRC datasets address general domains, they lack the specificity needed for cultural heritage information. Unfortunately, the manual creation of such datasets is prohibitively expensive for most heritage institutions. This paper presents a cost-effective approach for generating domain-specific MRC datasets with increased difficulty using Reinforcement Learning from Human Feedback (RLHF) from synthetic preference data. Our method leverages the performance of existing question-answering models on a subset of SQuAD to create a difficulty metric, assuming that more challenging questions are answered correctly less frequently. This research contributes: (1) A methodology for increasing question difficulty using PPO and synthetic data; (2) Empirical evidence of the method’s effectiveness, including human evaluation; (3) An in-depth error analysis and study of emergent phenomena; and (4) An open-source codebase and set of three llama-2-chat adapters for reproducibility and adaptation.

Instruction-tuned Large Language Models (LLMs) have exhibited impressive language understanding and the capacity to generate responses that follow specific prompts. However, due to the computational demands associated with training these models, their applications often adopt a zero-shot setting. In this paper, we evaluate the zero-shot performance of two publicly accessible LLMs, ChatGPT and OpenAssistant, in the context of six Computational Social Science classification tasks, while also investigating the effects of various prompting strategies. Our experiments investigate the impact of prompt complexity, including the effect of incorporating label definitions into the prompt; use of synonyms for label names; and the influence of integrating past memories during foundation model training. The findings indicate that in a zero-shot setting, current LLMs are unable to match the performance of smaller, fine-tuned baseline transformer models (such as BERT-large). Additionally, we find that different prompting strategies can significantly affect classification accuracy, with variations in accuracy and F1 scores exceeding 10%.