Burcu Sayin

Burcu Sayin, Jie Yang, Xinyue Chen et al.

In this paper, we argue that the prevailing approach to training and evaluating machine learning models often fails to consider their real-world application within organizational or societal contexts, where they are intended to create beneficial value for people. We propose a shift in perspective, redefining model assessment and selection to emphasize integration into workflows that combine machine predictions with human expertise, particularly in scenarios requiring human intervention for low-confidence predictions. Traditional metrics like accuracy and f-score fail to capture the beneficial value of models in such hybrid settings. To address this, we introduce a simple yet theoretically sound "value" metric that incorporates task-specific costs for correct predictions, errors, and rejections, offering a practical framework for real-world evaluation. Through extensive experiments, we show that existing metrics fail to capture real-world needs, often leading to suboptimal choices in terms of value when used to rank classifiers. Furthermore, we emphasize the critical role of calibration in determining model value, showing that simple, well-calibrated models can often outperform more complex models that are challenging to calibrate.

Debodeep Banerjee, Burcu Sayin, Stefano Teso et al.

Building on recent advances in AI, hybrid decision making (HDM) holds the promise of improving human decision quality and reducing cognitive load. We work in the context of learning to guide (LtG), a recently proposed HDM framework in which the human is always responsible for the final decision: rather than suggesting decisions, in LtG the AI supplies (textual) guidance useful for facilitating decision making. One limiting factor of existing approaches is that their guidance compounds information about all possible outcomes, and as a result it can be difficult to digest. We address this issue by introducing ConfGuide, a novel LtG approach that generates more succinct and targeted guidance. To this end, it employs conformal risk control to select a set of outcomes, ensuring a cap on the false negative rate. We demonstrate our approach on a real-world multi-label medical diagnosis task. Our empirical evaluation highlights the promise of ConfGuide.

Burcu Sayin, Ipek Baris Schlicht, Ngoc Vo Hong et al.

Clinical decision-making is inherently complex, often influenced by cognitive biases, incomplete information, and case ambiguity. Large Language Models (LLMs) have shown promise as tools for supporting clinical decision-making, yet their typical one-shot or limited-interaction usage may overlook the complexities of real-world medical practice. In this work, we propose a hybrid human-AI framework, MedSyn, where physicians and LLMs engage in multi-step, interactive dialogues to refine diagnoses and treatment decisions. Unlike static decision-support tools, MedSyn enables dynamic exchanges, allowing physicians to challenge LLM suggestions while the LLM highlights alternative perspectives. Through simulated physician-LLM interactions, we assess the potential of open-source LLMs as physician assistants. Results show open-source LLMs are promising as physician assistants in the real world. Future work will involve real physician interactions to further validate MedSyn's usefulness in diagnostic accuracy and patient outcomes.

Burcu Sayin, Ngoc Vo Hong, Ipek Baris Schlicht et al.

Clinical decision-making in emergency medicine demands rapid, accurate diagnoses under uncertainty. Despite benchmark progress, evidence for LLMs as interactive aids in live physician workflows remains sparse. MedSyn lets physicians iteratively query an LLM provided with the full clinical record while initially viewing only the chief complaint. Seven physicians (three seniors, four residents) completed baseline and AI-assisted sessions across 52 MIMIC-IV cases stratified by difficulty. Blinded evaluation showed residents' Hard-case correctness rose from 0.589 to 0.734; difficulty-standardised completely-correct rates confirmed a medium effect (Δ = 0.092; p = 0.071; d = 0.47). Automated metrics corroborated these gains: standardised any-match accuracy improved by 0.156 (p < 0.0001), and residents showed the largest F1 gain (Δ = 0.138; p < 0.0001). Dialogue analysis revealed expertise-dependent strategies (seniors asked targeted, hypothesis-driven questions; residents relied on broader queries) and cross-expertise concordance increased (Δ = 0.145; p < 0.0001). Interactive LLM support meaningfully enhances diagnostic reasoning.

Burcu Sayin, Pasquale Minervini, Jacopo Staiano et al.

We explore the potential of Large Language Models (LLMs) to assist and potentially correct physicians in medical decision-making tasks. We evaluate several LLMs, including Meditron, Llama2, and Mistral, to analyze the ability of these models to interact effectively with physicians across different scenarios. We consider questions from PubMedQA and several tasks, ranging from binary (yes/no) responses to long answer generation, where the answer of the model is produced after an interaction with a physician. Our findings suggest that prompt design significantly influences the downstream accuracy of LLMs and that LLMs can provide valuable feedback to physicians, challenging incorrect diagnoses and contributing to more accurate decision-making. For example, when the physician is accurate 38% of the time, Mistral can produce the correct answer, improving accuracy up to 74% depending on the prompt being used, while Llama2 and Meditron models exhibit greater sensitivity to prompt choice. Our analysis also uncovers the challenges of ensuring that LLM-generated suggestions are pertinent and useful, emphasizing the need for further research in this area.

Ipek Baris Schlicht, Zhixue Zhao, Burcu Sayin et al.

Equitable access to reliable health information is vital for public health, but the quality of online health resources varies by language, raising concerns about inconsistencies in Large Language Models (LLMs) for healthcare. In this study, we examine the consistency of responses provided by LLMs to health-related questions across English, German, Turkish, and Chinese. We largely expand the HealthFC dataset by categorizing health-related questions by disease type and broadening its multilingual scope with Turkish and Chinese translations. We reveal significant inconsistencies in responses that could spread healthcare misinformation. Our main contributions are 1) a multilingual health-related inquiry dataset with meta-information on disease categories, and 2) a novel prompt-based evaluation workflow that enables sub-dimensional comparisons between two languages through parsing. Our findings highlight key challenges in deploying LLM-based tools in multilingual contexts and emphasize the need for improved cross-lingual alignment to ensure accurate and equitable healthcare information.

Debodeep Banerjee, Stefano Teso, Burcu Sayin et al.

There is increasing interest in developing AIs for assisting human decision-making in high-stakes tasks, such as medical diagnosis, for the purpose of improving decision quality and reducing cognitive strain. Mainstream approaches team up an expert with a machine learning model to which safer decisions are offloaded, thus letting the former focus on cases that demand their attention. his separation of responsibilities setup, however, is inadequate for high-stakes scenarios. On the one hand, the expert may end up over-relying on the machine's decisions due to anchoring bias, thus losing the human oversight that is increasingly being required by regulatory agencies to ensure trustworthy AI. On the other hand, the expert is left entirely unassisted on the (typically hardest) decisions on which the model abstained. As a remedy, we introduce learning to guide (LTG), an alternative framework in which - rather than taking control from the human expert - the machine provides guidance useful for decision making, and the human is entirely responsible for coming up with a decision. In order to ensure guidance is interpretable} and task-specific, we develop SLOG, an approach for turning any vision-language model into a capable generator of textual guidance by leveraging a modicum of human feedback. Our empirical evaluation highlights the promise of \method on a challenging, real-world medical diagnosis task.

Markus Reuter, Tobias Lingenberg, Rūta Liepiņa et al.

Retrieval-Augmented Generation (RAG) is a promising approach to mitigate hallucinations in Large Language Models (LLMs) for legal applications, but its reliability is critically dependent on the accuracy of the retrieval step. This is particularly challenging in the legal domain, where large databases of structurally similar documents often cause retrieval systems to fail. In this paper, we address this challenge by first identifying and quantifying a critical failure mode we term Document-Level Retrieval Mismatch (DRM), where the retriever selects information from entirely incorrect source documents. To mitigate DRM, we investigate a simple and computationally efficient technique which we refer to as Summary-Augmented Chunking (SAC). This method enhances each text chunk with a document-level synthetic summary, thereby injecting crucial global context that would otherwise be lost during a standard chunking process. Our experiments on a diverse set of legal information retrieval tasks show that SAC greatly reduces DRM and, consequently, also improves text-level retrieval precision and recall. Interestingly, we find that a generic summarization strategy outperforms an approach that incorporates legal expert domain knowledge to target specific legal elements. Our work provides evidence that this practical, scalable, and easily integrable technique enhances the reliability of RAG systems when applied to large-scale legal document datasets.

Ipek Baris Schlicht, Burcu Sayin, Zhixue Zhao et al.

Equitable access to reliable health information is vital when integrating AI into healthcare. Yet, information quality varies across languages, raising concerns about the reliability and consistency of multilingual Large Language Models (LLMs). We systematically examine cross-lingual disparities in pre-training source and factuality alignment in LLM answers for multilingual healthcare Q&A across English, German, Turkish, Chinese (Mandarin), and Italian. We (i) constructed Multilingual Wiki Health Care (MultiWikiHealthCare), a multilingual dataset from Wikipedia; (ii) analyzed cross-lingual healthcare coverage; (iii) assessed LLM response alignment with these references; and (iv) conducted a case study on factual alignment through the use of contextual information and Retrieval-Augmented Generation (RAG). Our findings reveal substantial cross-lingual disparities in both Wikipedia coverage and LLM factual alignment. Across LLMs, responses align more with English Wikipedia, even when the prompts are non-English. Providing contextual excerpts from non-English Wikipedia at inference time effectively shifts factual alignment toward culturally relevant knowledge. These results highlight practical pathways for building more equitable, multilingual AI systems for healthcare.

Debodeep Banerjee, Burcu Sayin, Stefano Teso et al.

Medical decision-making is a critical task, where errors can result in serious, potentially life-threatening consequences. While full automation remains challenging, hybrid frameworks that combine machine intelligence with human oversight offer a practical alternative. In this paper, we present MedGellan, a lightweight, annotation-free framework that uses a Large Language Model (LLM) to generate clinical guidance from raw medical records, which is then used by a physician to predict diagnoses. MedGellan uses a Bayesian-inspired prompting strategy that respects the temporal order of clinical data. Preliminary experiments show that the guidance generated by the LLM with MedGellan improves diagnostic performance, particularly in recall and $F_1$ score.

Burcu Sayin, Jie Yang, Andrea Passerini et al.

We motivate why the science of learning to reject model predictions is central to ML, and why human computation has a lead role in this effort.

Jorge Ramírez, Burcu Sayin, Marcos Baez et al.

Crowdsourcing is being increasingly adopted as a platform to run studies with human subjects. Running a crowdsourcing experiment involves several choices and strategies to successfully port an experimental design into an otherwise uncontrolled research environment, e.g., sampling crowd workers, mapping experimental conditions to micro-tasks, or ensure quality contributions. While several guidelines inform researchers in these choices, guidance of how and what to report from crowdsourcing experiments has been largely overlooked. If under-reported, implementation choices constitute variability sources that can affect the experiment's reproducibility and prevent a fair assessment of research outcomes. In this paper, we examine the current state of reporting of crowdsourcing experiments and offer guidance to address associated reporting issues. We start by identifying sensible implementation choices, relying on existing literature and interviews with experts, to then extensively analyze the reporting of 171 crowdsourcing experiments. Informed by this process, we propose a checklist for reporting crowdsourcing experiments.

Evgeny Krivosheev, Burcu Sayin, Alessandro Bozzon et al.

In this paper, we explore how to efficiently combine crowdsourcing and machine intelligence for the problem of document screening, where we need to screen documents with a set of machine-learning filters. Specifically, we focus on building a set of machine learning classifiers that evaluate documents, and then screen them efficiently. It is a challenging task since the budget is limited and there are countless number of ways to spend the given budget on the problem. We propose a multi-label active learning screening specific sampling technique -- objective-aware sampling -- for querying unlabelled documents for annotating. Our algorithm takes a decision on which machine filter need more training data and how to choose unlabeled items to annotate in order to minimize the risk of overall classification errors rather than minimizing a single filter error. We demonstrate that objective-aware sampling significantly outperforms the state of the art active learning sampling strategies.