Large language models (LLMs) are increasingly used by children, yet their responses are often not tailored to young users’ reading levels or cognitive development. Previous attempts to improve content readability through prompt modifications such as adding "for kids" have shown limited success. This project explores an alternative strategy: persona-based prompting. Rather than directly specifying the target audience, we instruct the LLM to role-play a teacher as a familiar figure to children. Using real child authored queries, we evaluate whether this role-based approach leads to more readable and comprehensible responses across different LLMs. Readability and comprehension were measured using established metrics, including Flesch-Kincaid formulas and Age of Acquisition data. Our results show that for 4 out of the four evaluated models, persona based prompting consistently produces responses that are more readable and accessible across all readability metrics and some comprehensibility metrics compared to standard or intended-user prompting. This finding suggests that persona-based prompting is a promising strategy for improving the suitability of LLM outputs for young audiences.

As children increasingly turn to general-purpose search engines for learning and exploration, concerns arise about the relevance and safety of the content they encounter. These platforms are designed primarily for adults, often failing to deliver child-friendly results. One existing strategy is to append the phrase "for kids" to search queries, a technique previously shown to improve content relevance. However, those findings are outdated and based on limited evaluation methods. Since then, web content and search engine algorithms have evolved significantly, leaving an open question: how does this simple strategy impact the search quality for young users today? Since children continue encountering complex or unsafe content online, reassessing this approach is important. We aim to evaluate the impact of this query modification across three key dimensions: readability, language safety, and domain trustworthiness. Our results show that, while appending "for kids" modestly improves readability, it does not have a positive impact on the profanity rates or presence of unsafe URLs. These findings suggest that although the strategy remains partially effective, it is not a one-size-fits-all solution. This work highlights the need for more adaptive and child-aware search interventions in modern search environments.

Children often struggle to retrieve age-appropriate information when seeking information online. One big reason for this is that their search queries are short, misspelled, or vague. As a solution to this problem, previous research investigated query reformulation, where the input query is manipulated in a way that the retrieved web results are more child-appropriate. This was measured by various metrics and scores, such as readability and content safety of the retrieved web search results. The problem with present query reformulation strategies, however, is that each tackles this problem from one perspective, missing out on the potential benefits of other perspectives. For instance, expanding the query with the “for kids” cue has shown to be a good way to target a specific audience and helps retrieve more child-appropriate content; however, on top of this considering substitutes for uncommon words with simpler synonyms might further enhance the child-appropriateness of the retrieved results as it tackles the reformulation from a different perspective than “for kids” audience cue expansion.

Motivated by this, we propose a multi-step query reformulation strategy that combines multiple reformulation strategies and applies them to the given input child query in a multi-step manner using a Large Language Model (LLM). We use LLM to apply the reformulation strategies to the input query in a chain-of-calls (where each call is prompted to apply a different reformulation strategy). This proposed method captures the perspective of multiple reformulation strategies, rather than a single one, unlike existing reformulation strategies. The results of our experiments, which include a baseline comparison (of the retrieved search results from the reformulated query against the original query) and an ablation study, provide insight into the performance of our strategy.

With this work, we aim to demonstrate the potential of combining multiple reformulation strategies and their impact on improving the readability and content safety of retrieved web search results when applied to children’s search queries. Our findings reveal a significant improvement in the readability of retrieved results after using the proposed reformulation method. Ultimately, this work contributes to the development of next-generation, child-centric search systems that deliver clearer, safer results for children.

Children increasingly rely on web search engines to support their learning and exploration. However, conventional search systems are not optimised for their developmental stage, often returning information that is linguistically complex or educationally irrelevant. The retrieved results are often written at a higher reading grade level than children can easily comprehend, resulting in poor engagement and learning outcomes. This research investigates whether substituting simpler vocabulary into search queries can improve the educational relevance and readability of retrieved web content. We develop a reformulation pipeline consisting of: (1) a rule-based method that substitutes key query terms with synonyms ranked by Age of Acquisition (AoA) scores, and (2) a computational intelligence approach that uses a Large Language Model (LLM) to generate child-friendly rephrasings. The results retrieved from the queries are evaluated across two dimensions: readability and educational relevance. Our results show that rule-based reformulations improve readability, but retrieved results stayed consistent in terms of educational relevance. LLM-based reformulations enhance educational relevance; however, they don’t improve readability. This trade-off highlights the complementary strengths of both methods and underlines the potential of direct query reformulation to make web search more accessible and educationally effective for children.