Abstract:Hallucination detection in Large Language Models (LLMs) is crucial for ensuring their reliability. This work presents our participation in the CLEF ELOQUENT HalluciGen shared task, where the goal is to develop evaluators for both generating and detecting hallucinated content. We explored the capabilities of four LLMs: Llama 3, Gemma, GPT-3.5 Turbo, and GPT-4, for this purpose. We also employed ensemble majority voting to incorporate all four models for the detection task. The results provide valuable insights into the strengths and weaknesses of these LLMs in handling hallucination generation and detection tasks.
Abstract:Information retrieval systems have been evaluated using the Cranfield paradigm for many years. This paradigm allows a systematic, fair, and reproducible evaluation of different retrieval methods in fixed experimental environments. However, real-world retrieval systems must cope with dynamic environments and temporal changes that affect the document collection, topical trends, and the individual user's perception of what is considered relevant. Yet, the temporal dimension in IR evaluations is still understudied. To this end, this work investigates how the temporal generalizability of effectiveness evaluations can be assessed. As a conceptual model, we generalize Cranfield-type experiments to the temporal context by classifying the change in the essential components according to the create, update, and delete operations of persistent storage known from CRUD. From the different types of change different evaluation scenarios are derived and it is outlined what they imply. Based on these scenarios, renowned state-of-the-art retrieval systems are tested and it is investigated how the retrieval effectiveness changes on different levels of granularity. We show that the proposed measures can be well adapted to describe the changes in the retrieval results. The experiments conducted confirm that the retrieval effectiveness strongly depends on the evaluation scenario investigated. We find that not only the average retrieval performance of single systems but also the relative system performance are strongly affected by the components that change and to what extent these components changed.
Abstract:Simulating user interactions enables a more user-oriented evaluation of information retrieval (IR) systems. While user simulations are cost-efficient and reproducible, many approaches often lack fidelity regarding real user behavior. Most notably, current user models neglect the user's context, which is the primary driver of perceived relevance and the interactions with the search results. To this end, this work introduces the simulation of context-driven query reformulations. The proposed query generation methods build upon recent Large Language Model (LLM) approaches and consider the user's context throughout the simulation of a search session. Compared to simple context-free query generation approaches, these methods show better effectiveness and allow the simulation of more efficient IR sessions. Similarly, our evaluations consider more interaction context than current session-based measures and reveal interesting complementary insights in addition to the established evaluation protocols. We conclude with directions for future work and provide an entirely open experimental setup.
Abstract:This publication describes the motivation and generation of $Q_{bias}$, a large dataset of Google and Bing search queries, a scraping tool and dataset for biased news articles, as well as language models for the investigation of bias in online search. Web search engines are a major factor and trusted source in information search, especially in the political domain. However, biased information can influence opinion formation and lead to biased opinions. To interact with search engines, users formulate search queries and interact with search query suggestions provided by the search engines. A lack of datasets on search queries inhibits research on the subject. We use $Q_{bias}$ to evaluate different approaches to fine-tuning transformer-based language models with the goal of producing models capable of biasing text with left and right political stance. Additionally to this work we provided datasets and language models for biasing texts that allow further research on bias in online information search.
Abstract:Academic Search is a timeless challenge that the field of Information Retrieval has been dealing with for many years. Even today, the search for academic material is a broad field of research that recently started working on problems like the COVID-19 pandemic. However, test collections and specialized data sets like CORD-19 only allow for system-oriented experiments, while the evaluation of algorithms in real-world environments is only available to researchers from industry. In LiLAS, we open up two academic search platforms to allow participating research to evaluate their systems in a Docker-based research environment. This overview paper describes the motivation, infrastructure, and two systems LIVIVO and GESIS Search that are part of this CLEF lab.
Abstract:Considering the multimodal signals of search items is beneficial for retrieval effectiveness. Especially in web table retrieval (WTR) experiments, accounting for multimodal properties of tables boosts effectiveness. However, it still remains an open question how the single modalities affect user experience in particular. Previous work analyzed WTR performance in ad-hoc retrieval benchmarks, which neglects interactive search behavior and limits the conclusion about the implications for real-world user environments. To this end, this work presents an in-depth evaluation of simulated interactive WTR search sessions as a more cost-efficient and reproducible alternative to real user studies. As a first of its kind, we introduce interactive query reformulation strategies based on Doc2Query, incorporating cognitive states of simulated user knowledge. Our evaluations include two perspectives on user effectiveness by considering different cost paradigms, namely query-wise and time-oriented measures of effort. Our multi-perspective evaluation scheme reveals new insights about query strategies, the impact of modalities, and different user types in simulated WTR search sessions.
Abstract:Evaluating retrieval performance without editorial relevance judgments is challenging, but instead, user interactions can be used as relevance signals. Living labs offer a way for small-scale platforms to validate information retrieval systems with real users. If enough user interaction data are available, click models can be parameterized from historical sessions to evaluate systems before exposing users to experimental rankings. However, interaction data are sparse in living labs, and little is studied about how click models can be validated for reliable user simulations when click data are available in moderate amounts. This work introduces an evaluation approach for validating synthetic usage data generated by click models in data-sparse human-in-the-loop environments like living labs. We ground our methodology on the click model's estimates about a system ranking compared to a reference ranking for which the relative performance is known. Our experiments compare different click models and their reliability and robustness as more session log data becomes available. In our setup, simple click models can reliably determine the relative system performance with already 20 logged sessions for 50 queries. In contrast, more complex click models require more session data for reliable estimates, but they are a better choice in simulated interleaving experiments when enough session data are available. While it is easier for click models to distinguish between more diverse systems, it is harder to reproduce the system ranking based on the same retrieval algorithm with different interpolation weights. Our setup is entirely open, and we share the code to reproduce the experiments.
Abstract:The German Information Retrieval community is located in two different sub-fields: Information and computer science. There are no current studies that investigate these communities on a scientometric level. Available studies only focus on the information scientific part of the community. We generated a data set of 401 recent IR-related publications extracted from six core IR conferences from a mainly computer scientific background. We analyze this data set at the institutional and researcher level. The data set is publicly released, and we also demonstrate a mapping use case.
Abstract:Meta-evaluation studies of system performances in controlled offline evaluation campaigns, like TREC and CLEF, show a need for innovation in evaluating IR-systems. The field of academic search is no exception to this. This might be related to the fact that relevance in academic search is multilayered and therefore the aspect of user-centric evaluation is becoming more and more important. The Living Labs for Academic Search (LiLAS) lab aims to strengthen the concept of user-centric living labs for the domain of academic search by allowing participants to evaluate their retrieval approaches in two real-world academic search systems from the life sciences and the social sciences. To this end, we provide participants with metadata on the systems' content as well as candidate lists with the task to rank the most relevant candidate to the top. Using the STELLA-infrastructure, we allow participants to easily integrate their approaches into the real-world systems and provide the possibility to compare different approaches at the same time.
Abstract:In real-world Information Retrieval (IR) experiments, the Evaluation Environment (EE) is exposed to constant change. Documents are added, removed, or updated, and the information need and the search behavior of users is evolving. Simultaneously, IR systems are expected to retain a consistent quality. The LongEval Lab seeks to investigate the longitudinal persistence of IR systems, and in this work, we describe our participation. We submitted runs of five advanced retrieval systems, namely a Reciprocal Rank Fusion (RRF) approach, ColBERT, monoT5, Doc2Query, and E5, to both sub-tasks. Further, we cast the longitudinal evaluation as a replicability study to better understand the temporal change observed. As a result, we quantify the persistence of the submitted runs and see great potential in this evaluation method.