Large Language Models (LLMs) are increasingly used in Information Retrieval, both within retrieval pipelines and for constructing evaluation resources. Existing studies on using LLMs for IR evaluation, however, focus almost exclusively on English, leaving their applicability to other languages, where evaluation resources are often limited and highly needed, unexplored.

Large Language Models (LLMs) are increasingly used to replace human judges to assess the relevance of information objects, raising concerns about circularity, bias, and whether simulated preferences can substitute for human judgement. This work presents experiments using multiple LLMs to label passages for relevance. It examines their gullibility—how easily they are misled into labelling irrelevant passages as relevant. It also compares LLMs with human judges in ranking systems, analysing differences in discriminative power and whether some systems benefit under LLM-based evaluation. Results show that LLMs are influenced by the presence of query terms, even with irrelevant or random passages. Moreover, LLM-generated rankings are highly correlated with those of human judges, with strong agreement on which system is better in pairwise comparisons. However, LLMs may exhibit lower discriminative power, as seen in flatter ranking slopes and missed significance for meaningful improvements. Yet, there are no cases where capable LLMs and human judges reach opposing conclusions with significance. LLMs may boost traditional systems more than neural ones, adding a new concern of system bias. These findings highlight the strong potential of LLMs for relevance labelling, while also highlighting failure cases that call for careful adoption and further research to maintain evaluation integrity. 1

This paper explores the utility of a Large Language Model (LLM) to automatically generate queries and query variants from a description of an information need. Given a set of information needs described as backstories, we explore how similar the queries generated by the LLM are to those generated by humans. We quantify the similarity using different metrics and examine how the use of each set would contribute to document pooling when building test collections. Our results show potential in using LLMs to generate query variants. While they may not fully capture the wide variety of human-generated variants, they generate similar sets of relevant documents, reaching up to 71.1% overlap at a pool depth of 100.

In this research, we aim to examine the assumptions made about users when searching for non-factoid answers using search engines. That is, the way they approach non-factoid question-answering tasks, the language they use to express their questions, the variability in their queries and their behavior towards the provided answers. The investigation will also examine the extent to which these neglected factors affect retrieval performance and potentially highlight the importance of building more realistic methodologies and test collections that capture the real nature of this task. Through our preliminary work, we have begun to explore the characteristics of non-factoid question-answering queries and investigate query variability and their impact on modern retrieval models. Our preliminary results demonstrate notable differences between non-factoid questions sampled from a large query log and those used in QA datasets. In addition, our results demonstrate a profound effect of query variability on retrieval consistency, indicating a potential impact on retrieval performance that is worth studying. We highlight the importance of understanding user behaviour while searching for non-factoid answers, specifically the way they behave in response to receiving an answer. This should advance our understanding of the support users require across different types of non-factoid questions and inform the design of interaction models that support learning and encourage exploring.

Where do queries -- the words searchers type into a search box -- come from? The Information Retrieval community understands the performance of queries and search engines extensively, and has recently begun to examine the impact of query variation, showing that different queries for the same information need produce different results. In an information environment where bad actors try to nudge searchers toward misinformation, this is worrisome. The source of query variation -- searcher characteristics, contextual or linguistic prompts, cognitive biases, or even the influence of external parties -- while studied in a piecemeal fashion by other research communities has not been studied by ours. In this paper we draw on a variety of literatures (including information seeking, psychology, and misinformation), and report some small experiments to describe what is known about where queries come from, and demonstrate a clear literature gap around the source of query variations in IR. We chart a way forward for IR to research, document and understand this important question, with a view to creating search engines that provide more consistent, accurate and relevant search results regardless of the searcher's framing of the query.