We are living in an era of "big literature", where the volume of digital scientific publications is growing exponentially. While offering new opportunities, this also poses challenges for understanding literature landscapes, as traditional manual reviewing is no longer feasible. Recent large language models (LLMs) have shown strong capabilities for literature comprehension, yet they are incapable of offering "comprehensive, objective, open and transparent" views desired by systematic reviews due to their limited context windows and trust issues like hallucinations. Here we present LitChat, an end-to-end, interactive and conversational literature agent that augments LLM agents with data-driven discovery tools to facilitate literature exploration. LitChat automatically interprets user queries, retrieves relevant sources, constructs knowledge graphs, and employs diverse data-mining techniques to generate evidence-based insights addressing user needs. We illustrate the effectiveness of LitChat via a case study on AI4Health, highlighting its capacity to quickly navigate the users through large-scale literature landscape with data-based evidence that is otherwise infeasible with traditional means.
论文检索
输入标题、作者或关键词，从 7,537 篇学术成果中精准定位
Matching markets, where agents are assigned to one another based on preferences and constraints, are fundamental in various AI-driven applications such as school choice, content matching, and recommender systems. A key challenge in these markets is understanding preference data, as the interpretability of algorithmic solutions hinges on accurately capturing and explaining preferences. We introduce MatchXplain, a platform that integrates preference explanation with a robust matching engine. MatchXplain offers a layered approach for explaining preferences, computing diverse matching solutions, and providing interactive visualizations to enhance user understanding. By bridging algorithmic decision-making with explainability, MatchXplain improves transparency and trust in algorithmic matching markets.
Large Language Models (LLMs) have become integral to human decision-making processes. However, their outputs are not always reliable, often requiring users to assess the accuracy of the information provided manually. This issue is exacerbated by hallucinated responses, which are frequently presented with convincing but incorrect explanations, leading to trust concerns among users. To address this challenge, we propose GE-Chat, a knowledge Graph-enhanced retrieval-augmented generation framework designed to deliver Evidence-based responses. Specifically, when users upload a document, GE-Chat constructs a knowledge graph to support a retrieval-augmented agent, enriching the agent's responses with external knowledge beyond its training data. We further incorporate Chain-of-Thought (CoT) reasoning, n-hop subgraph searching, and entailment-based sentence generation to ensure accurate evidence retrieval. Experimental results demonstrate that our approach improves the ability of existing models to identify precise evidence in free-form contexts, offering a reliable mechanism for verifying LLM-generated conclusions and enhancing trustworthiness.
TimelyMed: AI-Driven Clinical Course Attribution and Temporal Mapping for Psychiatric Medical Records
PDF ↗Timely understanding of a patient’s clinical course is crucial for effective treatment. Extracting course-related information, such as temporal and medical events, from unstructured medical records is both challenging and time-consuming, especially when relying on manual identification by physicians. We introduce TimelyMed, a system powered by a locally deployed large language model (LLM) that ensures data security while efficiently organizing key psychiatric events and their corresponding temporal information. Additionally, our system is attributed, allowing clinicians to not only categorize events but also trace them back to their original textual descriptions, ensuring transparency and interpretability in clinical decision-making. By organizing temporal and medical event information into timelines, our system enables physicians to quickly grasp a patient’s medical history while effectively reducing their cognitive burden.
Time series modeling is essential in finance, healthcare, and environmental science, yet nonlinear patterns, noise, and concept drift pose challenges. Although deep learning models, such as Transformer-based and recent pre-trained models, have achieved good performance across various time series tasks, they often lack interpretability, especially in co-evolving time series. This work introduces a kernel representation learning (KRL) perspective, rethinking time series modeling through kernel-induced self-representation to effectively capture temporal structures and dynamic transitions. Additionally, we establish theoretical connections between KRL and advanced deep-network models, demonstrating how kernel methods provide a principled approach to capturing complex time series behaviors.
Feature attribution methods explain model predictions by assigning importance to input features. Choosing the most suitable method is difficult due to inconsistencies and a lack of universal solutions. Our research focuses on proposing tools and methodologies for evaluating, comparing, and selecting these methods.
AI models are increasingly accessible through chatbots and other applications, but their black-box nature and sensitivity to small changes in the input make them hard to interpret and trust. Existing correlation-based robustness metrics fail to explain model errors or isolate causal effects. To address this, I propose ARC (AI Rating through Causality), a causally-grounded framework for rating AI models based on their robustness. ARC evaluates robustness by quantifying statistical and confounding biases, as well as the impact of perturbations on model performance across diverse tasks. ARC produces interpretable raw scores and ratings, helping developers and users make informed decisions about model robustness. Two future directions include: (1) deriving raw scores for composite models from their component scores, and (2) combining ratings with traditional explainable AI approaches to provide a more holistic view of model behavior.
With approximately 2 billion chest X-ray examinations conducted globally each year, the demand for radiological interpretation far surpasses the available expertise, particularly in resource-constrained regions. Recent advancements in artificial intelligence and computer vision present promising solutions for automated chest X-ray analysis. Nevertheless, integrating AI-driven diagnostics into clinical practice encounters several challenges, including data-centric issues, implementation barriers, deployment complexities, and the need for trustworthy AI. This dissertation focuses on the data-centric aspect, making significant contributions through enhanced data collection, the creation of novel datasets, algorithm development, privacy-preserving collaborative learning, and modelling for low-resolution data. It offers practical methodologies for embedding AI into chest radiology workflows, with a particular emphasis on addressing underserved conditions and healthcare settings with limited data availability. Furthermore, this work illustrates how tailored AI solutions can democratize access to high-quality radiological care while balancing privacy considerations and operational constraints across diverse environments.
Credulous Acceptance in High-Order Argumentation Frameworks with Necessities: An Incremental Approach (Abstract Reprint)
PDF ↗Argumentation is an important research area in the field of AI. There is a substantial amount of work on different aspects of Dung's abstract Argumentation Framework (AF). Two relevant aspects considered separately so far are: i) extending the framework to account for recursive attacks and supports, and ii) considering dynamics, i.e., AFs evolving over time. In this paper, we jointly deal with these two aspects. We focus on High-Order Argumentation Frameworks with Necessities (HOAFNs) which allow for attack and support relations (interpreted as necessity) not only between arguments but also targeting attacks and supports at any level. We propose an approach for the incremental evaluation of the credulous acceptance problem in HOAFNs, by “incrementally” computing an extension (a set of accepted arguments, attacks and supports), if it exists, containing a given goal element in an updated HOAFN. In particular, we are interested in monitoring the credulous acceptance of a given argument, attack or support (goal) in an evolving HOAFN. Thus, our approach assumes to have a HOAFN Δ, a goal ϱ occurring in Δ, an extension E for Δ containing ϱ, and an update u establishing some changes in the original HOAFN, and uses the extension for first checking whether the update is relevant; for relevant updates, an extension of the updated HOAFN containing the goal is computed by translating the problem to the AF domain and leveraging on AF solvers. We provide formal results for our incremental approach and empirically show that it outperforms the evaluation from scratch of the credulous acceptance problem for an updated HOAFN.
Pretrained language models (PLMs) achieve state-of-the-art results but often function as ``black boxes'', hindering interpretability and responsible deployment. While methods like attention analysis exist, they often lack clarity and intuitiveness. We propose interpreting PLMs through high-level, human-understandable concepts using Concept Bottleneck Models (CBMs). This extended abstract introduces C3M (ChatGPT-guided Concept augmentation with Concept-level Mixup), a novel framework for training Concept-Bottleneck-Enabled PLMs (CBE-PLMs). C3M leverages Large Language Models (LLMs) like ChatGPT to augment concept sets and generate noisy concept labels, combined with a concept-level MixUp mechanism to enhance robustness and effectively learn from both human-annotated and machine-generated concepts. Empirical results show our approach provides intuitive explanations, aids model diagnosis via test-time intervention, and improves the interpretability-utility trade-off, even with limited or noisy concept annotations. This is an concise version of [Tan et al., 2024b], recipient of the Best Paper Award at PAKDD 2024. Code and data are released at https://github.com/Zhen-Tan-dmml/CBM_NLP.git.
CAM-based methods are widely-used post-hoc interpretability methods that produce a saliency map to explain the decision of an image classification model. The saliency map highlights the important areas of the image relevant to the prediction. In this paper, we show that most of these methods can incorrectly attribute an important score to parts of the image that the model cannot see. We show that this phenomenon occurs both theoretically and experimentally. On the theory side, we analyze the behavior of GradCAM on a simple masked CNN model at initialization. Experimentally, we train a VGG-like model constrained to not use the lower part of the image and nevertheless observe positive scores in the unseen part of the image. This behavior is evaluated quantitatively on two new datasets. We believe that this is problematic, potentially leading to mis-interpretation of the model's behavior.
We design a lightweight structural feature extraction technique for graph classification. It leverages node subsets and connection strength reflected by random-walk-based heuristics, presenting a scalable, unsupervised, and easily interpretable alternative. We provide theoretical insights into our technical design and establish a relation between the extracted structural features and the graph spectrum. We show our method achieves high levels of computational efficiency while maintaining robust classification accuracy.
According to meaning holism, the meanings of all the words in a language are interdependent. If this was true, then the very practice of building largely interconnected set of ontologies would be threatened. We examine here the extent of the severity of meaning holism for ontology engineering, based on a definition of the meaning of a class term in an ontology, with regard to the classical analytic/synthetic distinction. We show that meaning holism is not as pervasive in ontologies as traditionally assumed in philosophy of language when interpreting the meaning of a class term as a collection of statements expressing necessary conditions on this term. Still, meaning holism presents substantial challenges for ontology engineering and requires mitigation strategies. We also investigate the related phenomenon of indeterminacy of reference and show how anchoring formal ontologies in natural language can mitigate this problem, even if not fully control it.
Decision trees are a popular tool in machine learning and yield easy-to-understand models. Several techniques have been proposed in the literature for learning a decision tree classifier, with different techniques working well for data from different domains. In this work, we develop a data-driven approach to design decision tree learning algorithms given repeated access to data from the same domain. We study multiple formulations covering different aspects and popular techniques for learning decision trees. We propose novel parameterized classes of node splitting criteria in top-down algorithms, which interpolate between popularly used entropy and Gini impurity based criteria, and provide theoretical bounds on the number of samples needed to learn the splitting function appropriate for the data at hand. We also study the sample complexity of tuning prior parameters in Bayesian decision tree learning, and extend our results to decision tree regression. We further consider the problem of tuning hyperparameters in pruning the decision tree for classical pruning algorithms including min-cost complexity pruning. We also study the interpretability of the learned decision trees and introduce a data-driven approach for optimizing the explainability versus accuracy trade-off using decision trees. Finally, we demonstrate the significance of our approach on real world datasets by learning data-specific decision trees which are simultaneously more accurate and interpretable.
With the rapid advancements in multi-modal large language models (MLLMs), connectors play a pivotal role in bridging diverse modalities and enhancing model performance. However, the design and evolution of connectors have not been comprehensively analyzed, leaving gaps in understanding how these components function and hindering the development of more powerful connectors. In this survey, we systematically review the current progress of connectors in MLLMs and present a structured taxonomy that categorizes connectors into atomic operations (mapping, compression, mixture of experts) and holistic designs (multi-layer, multi-encoder, multi-modal scenarios), highlighting their technical contributions and advancements. Furthermore, we discuss several promising research frontiers and challenges, including high-resolution input, dynamic compression, guide information selection, combination strategy, and interpretability. This survey is intended to serve as a foundational reference and a clear roadmap for researchers, providing valuable insights into the design and optimization of next-generation connectors to enhance the performance and adaptability of MLLMs.
Game theory establishes a fundamental framework for analyzing strategic interactions among rational decision-makers. The rapid advancement of large language models (LLMs) has sparked extensive research exploring the intersection of these two fields. Specifically, game-theoretic methods are being applied to evaluate and enhance LLM capabilities, while LLMs themselves are reshaping classic game models. This paper presents a comprehensive survey of the intersection of these fields, exploring a bidirectional relationship from three perspectives: (1) Establishing standardized game-based benchmarks for evaluating LLM behavior; (2) Leveraging game-theoretic methods to improve LLM performance through algorithmic innovations; (3) Characterizing the societal impacts of LLMs through game modeling. Among these three aspects, we also highlight how the equilibrium analysis for traditional game models is impacted by LLMs' advanced language understanding, which in turn extends the study of game theory. Finally, we identify key challenges and future research directions, assessing their feasibility based on the current state of the field. By bridging theoretical rigor with emerging AI capabilities, this survey aims to foster interdisciplinary collaboration and drive progress in this evolving research area.
Classical information theory, a cornerstone of artificial intelligence, is fundamentally limited by its local perspective, often analyzing pairwise interactions while ignoring the larger, hierarchical architecture of complex systems. Structural entropy (SE) presents a paradigm shift, extending Shannon entropy to quantify information on a global scale and measure the uncertainty embedded in a system's organizational hierarchy. Although its applications have broadened significantly from its origins in community detection across diverse AI domains, a systematic synthesis of its theory, computational methods, and applications is currently lacking. This survey provides a comprehensive overview of SE to fill this critical void in the literature. We offer a detailed examination of its theoretical foundations, computational frameworks, and key learning paradigms, with a focus on its integration with graph learning and reinforcement learning. Through an exploration of its diverse applications, we highlight the power of SE to advance graph-based analysis and modeling. Finally, we discuss key challenges and future research opportunities for incorporating SE principles into the development of more interpretable and theoretically grounded AI systems.
The integration of symbolic computing with neural networks has intrigued researchers since the first theorizations of Artificial intelligence (AI). The ability of Neuro-Symbolic (NeSy) methods to infer or exploit behavioral schema has been widely considered as one of the possible proxies for human-level intelligence. However, the limited semantic generalizability and the challenges in declining complex domains with pre-defined patterns and rules hinder their practical implementation in real-world scenarios. The unprecedented results achieved by connectionist systems since the last AI breakthrough in 2017 have raised questions about the competitiveness of NeSy solutions, with particular emphasis on the Natural Language Processing and Computer Vision fields. This survey examines task-specific advancements in the NeSy domain to explore how incorporating symbolic systems can enhance explainability and reasoning capabilities. Our findings are meant to serve as a resource for researchers exploring explainable NeSy methodologies for real-life tasks and applications. Reproducibility details and in-depth comments on each surveyed research work are made available at https://github.com/disi-unibo-nlp/task-oriented-neuro-symbolic.git.
Large language models (LLMs) have achieved remarkable successes on various tasks. However, recent studies have found that there are still significant challenges to the logical reasoning abilities of LLMs, which can be categorized into the following two aspects: (1) Logical question answering: LLMs often fail to generate the correct answer within a complex logical problem which requires sophisticated deductive, inductive or abductive reasoning given a collection of premises and constrains. (2) Logical consistency: LLMs are prone to producing responses contradicting themselves across different questions. For example, a state-of-the-art question-answering LLM Macaw, answers Yes to both questions Is a magpie a bird? and Does a bird have wings? but answers No to Does a magpie have wings?. To facilitate this research direction, we comprehensively investigate the most cutting-edge methods and propose a detailed taxonomy. Specifically, to accurately answer complex logic questions, previous methods can be categorized based on reliance on external solvers, prompts, and fine-tuning. To avoid logical contradictions, we discuss concepts and solutions of various logical consistencies, including implication, negation, transitivity, factuality consistencies, and their composites. In addition, we review commonly used benchmark datasets and evaluation metrics, and discuss promising research directions, such as extending to modal logic to account for uncertainty and developing efficient algorithms that simultaneously satisfy multiple logical consistencies.
Deep learning models have shown promise in lung pathology detection from chest X-rays, but widespread clinical adoption remains limited due to opaque model decision-making. In prior work, we introduced ClinicXAI, a human-centric, expert-guided concept bottleneck model (CBM) designed for interpretable lung cancer diagnosis. We now extend that approach and present XpertXAI, a generalizable expert-driven model that preserves human-interpretable clinical concepts while scaling to detect multiple lung pathologies. Using a high-performing InceptionV3-based classifier and a public dataset of chest X-rays with radiology reports, we compare XpertXAI against leading post-hoc explainability methods and an unsupervised CBM, XCBs. We assess explanations through comparison with expert radiologist annotations and medical ground truth. Although XpertXAI is trained for multiple pathologies, our expert validation focuses on lung cancer. We find that existing techniques frequently fail to produce clinically meaningful explanations, omitting key diagnostic features and disagreeing with radiologist judgments. XpertXAI not only outperforms these baselines in predictive accuracy but also delivers concept-level explanations that better align with expert reasoning. While our focus remains on explainability in lung cancer detection, this work illustrates how human-centric model design can be effectively extended to broader diagnostic contexts — offering a scalable path toward clinically meaningful explainable AI in medical diagnostics.