Information Access Systems (IASs), such as Search Engines (SEs) and Large Language Model-based conversational agents (LLM-CAs), have become central tools through which users access information online. Their widespread use extends to children, who increasingly rely on these systems for learning and entertainment. However, children cannot be treated like adults as they differ in their suitability requirements.

Current IASs are primarily designed and optimized around general users, despite children having distinct requirements. At the same time, recent developments in generative AI have added more ways in which information is accessed, with LLM-CAs providing a conversational search approach and SEs increasingly integrating AI-generated summaries into presented results. Existing research has investigated children’s interactions with online information environments, yet it remains under-explored whether modern IASs textually portray content in ways that fit children’s needs across both retrieval-based and generative forms of information access. In addition, IASs operate across languages that differ in linguistic structure, content availability, and system support, making findings in one language not necessarily generalisable to others. As children’s information needs differ from those of adults, and most existing IASs are primarily designed for general audiences, questions arise regarding the suitability of these systems for child users. Therefore this work investigates the suitability of portrayed content for children across IASs and languages, focusing on two complementary dimensions: comprehension and harm exposure. Comprehension is operationalized through readability, ambiguity, and concreteness measures, while harm exposure is investigated through the detection of potentially harmful content categories, including harassment, hate speech, sexual content, and violent content. We conduct an empirical investigation using child-written queries in English and Dutch, collecting responses from traditional SEs and LLM-CAs. The response types we obtain from these two types of IASs consist of SERP results, AI-generated search summaries, retrieved webpages, and LLM-CA responses. To investigate suitability, the responses were investigated using a collection of automated indicators associated with child comprehension and harm exposure. In addition to comparing different systems and response types, the study examined differences between child-written and general-user queries as well as differences between English and Dutch responses.

The results suggest that currently adopted IASs display varying degrees of child suitability. Responses to child-written queries consistently achieved higher readability scores than responses to general user queries. However, improvements in readability did not consistently extend to improvements in ambiguity and concreteness. In contrast, harm-exposure scores remained low across the investigated response types, suggesting positively limited exposure of users to overtly harmful content. Furthermore, the investigation revealed that suitability characteristics do not always generalise across different languages. while readability-related findings remained relatively stable between English and Dutch, ambiguity and concreteness measures showed several language-connected differences. ... Read more

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. ... Read more

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. ... Read more

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. ... Read more

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. ... Read more