论文检索

Kehan Guo, Yili Shen, Gisela Abigail Gonzalez-Montiel, Yue Huang, Yujun Zhou, Mihir Surve, Zhichun Guo, Payel Das, Nitesh V. Chawla, Olaf Wiest 等

The rapid advent of machine learning (ML) and artificial intelligence (AI) has catalyzed major transformations in chemistry, yet the application of these methods to spectroscopic and spectrometric data—termed Spectroscopy Machine Learning (SpectraML)—remains relatively underexplored. Modern spectroscopic techniques (MS, NMR, IR, Raman, UV-Vis) generate an ever-growing volume of high-dimensional data, creating a pressing need for automated and intelligent analysis beyond traditional expert-based workflows. In this survey, we provide a unified review of SpectraML, systematically examining state-of-the-art approaches for both forward tasks (molecule-to-spectrum prediction) and inverse tasks (spectrum-to-molecule inference). We trace the historical evolution of ML in spectroscopy—from early pattern recognition to the latest foundation models capable of advanced reasoning—and offer a taxonomy of representative neural architectures, including graph-based and transformer-based methods. Addressing key challenges such as data quality, multimodal integration, and computational scalability, we highlight emerging directions like synthetic data generation, large-scale pretraining, and few- or zero-shot learning. To foster reproducible research, we release an open-source repository containing curated datasets and code implementations. Our survey serves as a roadmap for researchers, guiding advancements at the intersection of spectroscopy and AI.

Tamara C.P. Florijn, Pınar Yolum, Tim Baarslag

One-to-many negotiations are widely applied in various domains, contributing to efficient resource allocation and effective decision making. This wide variety of applications also brings a wide variety of implemented protocols, terminology and utility functions, which makes it hard to compare and improve strategies using existing solutions. We introduce a meta-model of negotiations, which characterizes almost all one-to-many negotiation research, bringing a unified description of the negotiations. This meta-model allows us to identify different classes of interdependency based on utility functions. We show how existing one-to-many negotiations are related to each other, finding new insights and identifying knowledge gaps. We suggest that a general utility function framework and benchmark scenarios for one-to-many negotiations could accommodate future advancement in this field.

Didier Dubois, Henri Prade

Possibilistic logic is forty years old. Possibilistic logic is a logic that handles classical logic formulas associated with weights taking values in a linearly ordered set or more generally in a lattice. Over the decades, possibilistic logic has undergone numerous developments at both theoretical and applied levels. The ambition of this article is to review all these developments while exposing the main ideas behind them.

Giovanni Pio Delvecchio, Lorenzo Molfetta, Gianluca Moro

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.

Shuai Cheng, Zhao Li, Shu Meng, Mengxia Ren, Haitao Xu, Shuai Hao, Chuan Yue, Fan Zhang

Large Language Models (LLMs) have demonstrated exceptional success across a variety of tasks, particularly in natural language processing, leading to their growing integration into numerous facets of daily life. However, this widespread deployment has raised substantial privacy concerns, especially regarding personally identifiable information (PII), which can be directly associated with specific individuals. The leakage of such information presents significant real-world privacy threats. In this paper, we conduct a systematic investigation into existing research on PII leakage in LLMs, encompassing commonly utilized PII datasets, evaluation metrics, and current studies on both PII leakage attacks and defensive strategies. Finally, we identify unresolved challenges in the current research landscape and suggest future research directions.

Fengxiang Cheng, Haoxuan Li, Fenrong Liu, Robert van Rooij, Kun Zhang, Zhouchen Lin

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.

Jiehua Chen, Joanna Kaczmarek, Paul Nüsken, Jörg Rothe, Ildikó Schlotter, Tessa Seeger

We survey the notion of control in various areas of computational social choice (COMSOC) such as voting, fair allocation, cooperative game theory, matching under preferences, and group identification. In all these scenarios, control can be exerted, for instance, by adding or deleting agents with the goal of influencing the outcome. We conclude by briefly covering control in some other COMSOC areas including participatory budgeting, judgment aggregation, and opinion diffusion.

John Burden, Marko Tešić, Lorenzo Pacchiardi, José Hernández-Orallo

Research in AI evaluation has grown increasingly complex and multidisciplinary, attracting researchers with diverse backgrounds and objectives. As a result, divergent evaluation paradigms have emerged, often developing in isolation, adopting conflicting terminologies, and overlooking each other's contributions. This fragmentation has led to insular research trajectories and communication barriers both among different paradigms and with the general public, contributing to unmet expectations for deployed AI systems. To help bridge this insularity, in this paper we survey recent work in the AI evaluation landscape and identify six main paradigms. We characterise major recent contributions within each paradigm across key dimensions related to their goals, methodologies and research cultures. By clarifying the unique combination of questions and approaches associated with each paradigm, we aim to increase awareness of the breadth of current evaluation approaches and foster cross-pollination between different paradigms. We also identify potential gaps in the field to inspire future research directions.

Pascal Bercher, Sarath Sreedharan, Mauro Vallati

Accurate planning models are a prerequisite for the appropriate functioning of AI planning applications. Creating these models is, however, a tedious and error-prone task -- even for planning experts. This makes the provision of automated modeling support essential. In this work, we differentiate between approaches that learn models from scratch (called domain model acquisition) and those that repair flawed or incomplete ones. We survey approaches for the latter, including those that can be used for domain repair but have been developed for other applications, discuss possible optimization metrics (i.e., which repaired model to aim at), and conclude with lines of research we believe deserve more attention.

Kamal Acharya, Iman Sharifi, Mehul Lad, Liang Sun, Houbing Song

Neurosymbolic AI combines neural network adaptability with symbolic reasoning, promising an approach to address the complex regulatory, operational, and safety challenges in Advanced Air Mobility (AAM). This survey reviews its applications across key AAM domains such as demand forecasting, aircraft design, and real-time air traffic management. Our analysis reveals a fragmented research landscape where methodologies, including Neurosymbolic Reinforcement Learning, have shown potential for dynamic optimization but still face hurdles in scalability, robustness, and compliance with aviation standards. We classify current advancements, present relevant case studies, and outline future research directions aimed at integrating these approaches into reliable, transparent AAM systems. By linking advanced AI techniques with AAM’s operational demands, this work provides a concise roadmap for researchers and practitioners developing next-generation air mobility solutions.

Haohao Zhu, Tingting Li, Peng He, Jiayu Zhou

Automated assessment of open responses in K–12 science education poses significant challenges due to the multimodal nature of student work, which often integrates textual explanations, drawings, and handwritten elements. Traditional evaluation methods that focus solely on textual analysis fail to capture the full breadth of student reasoning and are susceptible to biases such as handwriting neatness or answer length. In this paper, we propose a novel LLM-augmented multimodal evaluation framework that addresses these limitations through a comprehensive, bias-corrected grading system. Our approach leverages LLMs to generate causal knowledge graphs that encapsulate the essential conceptual relationships in student responses, comparing these graphs with those derived automatically from the rubrics and submissions. Experimental results demonstrate that our framework improves grading accuracy and consistency over deep supervised learning and few-shot LLM baselines.

Zahra Zahedi, Shashank Mehrotra, Teruhisa Misu, Kumar Akash

For future human-autonomous vehicle (AV) interactions to be effective and smooth, human-aware systems that analyze and align human needs with automation decisions are essential. Achieving this requires systems that account for human cognitive states. We present a novel computational model in the form of a Dynamic Bayesian Network (DBN) that infers the cognitive states of both AV users and other road users, integrating this information into the AV's decision-making process. Specifically, our model captures the ``well-being'' of both an AV user and an interacting road user as cognitive states alongside trust. Our DBN models infer beliefs over the AV user’s evolving well-being, trust, and intention states, as well as the possible well-being of other road users, based on observed interaction experiences. Using data collected from an interaction study, we refine the model parameters and empirically assess its performance. Finally, we extend our model into a causal inference model (CIM) framework for AV decision-making, enabling the AV to enhance user well-being and trust while balancing these factors with its own operational costs and the well-being of interacting road users. Our evaluation demonstrates the model’s effectiveness in accurately predicting user's states and guiding informed, human-centered AV decisions.

Wei Xiang, Ziyue Lei, Haoyuan Che, Fangyuan Ye, Xueting Wu, Lingyun Sun

Operational skill learning, inherently physical and reliant on hands-on practice and kinesthetic feedback, has yet to be effectively replicated in large language model (LLM)-supported training. Current LLM training assistants primarily generate customized textual feedback, neglecting the crucial kinesthetic modality. This gap derives from the textual and uncertain nature of LLMs, compounded by concerns on user acceptance of LLM driven body control. To bridge this gap and realize the potential of collaborative human-LLM action, this work explores human experience of LLM driven kinesthetic assistance. Specifically, we introduced an "Align-Analyze-Adjust" strategy and developed FlightAxis, a tool that integrates LLM with Electrical Muscle Stimulation (EMS) for flight skill acquisition, a representative operational skill domain. FlightAxis learns flight skills from manuals and guides forearm movements during simulated flight tasks. Our results demonstrate high user acceptance of LLM-mediated body control and significantly reduced task completion times. Crucially, trainees reported that this kinesthetic assistance enhanced their awareness of operation flaws and fostered increased engagement in the training process, rather than relieving perceived load. This work demonstrated the potential of kinesthetic LLM training in operational skill acquisition.

Amy Rafferty, Rishi Ramaesh, Ajitha Rajan

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.

Antonio Lieto, Gian Luca Pozzato, Stefano Zoia

We propose a system called METCL (Metaphor Elaboration in Typicality-Based Compositional Logic) able to generate and identify metaphors by using the TCL reasoning framework, specialized in human-like commonsense concept combination. We show that METCL is able to improve both state of-the-art Large Language Models (e.g DeepSeek-R1, GPT-4o, Qwen2.5-Max) and symbolic ones in the task of metaphor identification. Additionally, we show how the metaphors generated by METCL are generally well accepted by human subjects. The obtained results are encouraging and pave the way to research in automatic metaphor generation and comprehension based on the assumption that metaphors interpretation can be partially regarded as a categorization problem relying on generative commonsense concept combination.

Qihao Liang, Xichu Ma, Torin Hopkins, Ye Wang

Textbook reading has long dominated classical poetry education in Chinese-speaking communities. However, research has shown that extensive text-based learning can lead to learner disengagement and a less pleasant experience. This paper aims to improve the experience of classical Chinese poetry learning by introducing LivePoem—a system that generates musical storyboards (storyboards with background music) as audiovisual aids to support poetry comprehension. We employ a pre-trained diffusion model for storyboard generation and train a prosody-based poem-to-melody generator using a Transformer model, both validated by standard objective metrics to ensure generation quality. Through a within-subjects study involving 25 non-native Chinese learners, we compared learning outcomes from textbook reading and musical storyboard viewing through standardised reading comprehension tests. Additionally, the learning experience was assessed by the Self-Assessment Manikin (SAM) and an inductive thematic analysis of learners' open-ended feedback. Experimental results show that musical storyboards retained the learning outcomes of textbooks, while more effectively engaging learners and providing a more pleasant learning experience.

Tom Kouwenhoven, Max Peeperkorn, Roy de Kleijn, Tessa Verhoef

Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human, LLM-LLM and Human-LLM experiments. We show that referentially grounded vocabularies emerge that enable reliable communication in all conditions, even when humans and LLMs collaborate. Comparisons between conditions reveal that languages optimised for LLMs subtly differ from those optimised for humans. Interestingly, interactions between humans and LLMs alleviate these differences and result in vocabularies more human-like than LLM-like. These findings advance our understanding of the role inductive biases in LLMs play in the dynamic nature of human language and contribute to maintaining alignment in human and machine communication. In particular, our work underscores the need to think of new LLM training methods that include human interaction and shows that using communicative success as a reward signal can be a fruitful, novel direction.

Lin Jiang, Yu Yang, Guang Wang

Order dispatch systems play a vital role in ride-hailing services, which directly influence operator revenue, driver profit, and passenger experience. Most existing work focuses on improving system efficiency in terms of operator revenue, which may cause a bad experience for both passengers and drivers. Hence, in this work, we aim to design a human-centered ride-hailing system by considering both passenger fairness and driver preference without compromising the overall system efficiency. However, it is nontrivial to achieve this target due to the potential conflicts between passenger fairness and driver preference since optimizing one may sacrifice the other. To address this challenge, we design HCRide, a Human-Centered Ride-hailing system based on a novel multi-agent reinforcement learning algorithm called Harmonization-oriented Actor-Bi-Critic (Habic), which includes three major components (i.e., a multi-agent competition mechanism, a dynamic Actor network, and a Bi-Critic network) to optimize system efficiency and passenger fairness with driver preference consideration. We extensively evaluate our HCRide using two real-world ride-hailing datasets from Shenzhen and New York City. Experimental results show our HCRide effectively improves system efficiency by 2.02%, fairness by 5.39%, and driver preference by 10.21% compared to state-of-the-art baselines.

Guangrui Fan, Dandan Liu, Lihu Pan, Yishan Huang

Human–AI collaboration is increasingly integral to a variety of domains where creative ideation unfolds in iterative cycles, yet most existing studies evaluate AI-generated concepts in a single step. This paper addresses the gap by investigating “Creative Momentum Transfer”—how the timing (early vs. late) and labeling (AI-labeled vs. unlabeled) of AI prompts shape multi-round human ideation. In a between-subjects experiment (N = 247), participants proposed solutions for plastic pollution over two rounds, with AI suggestions introduced either at the outset or mid-process and labeled explicitly or not. Results reveal that early AI prompts increase overall creativity but induce stronger anchoring, whereas late AI prompts trigger a mid-round pivot that fosters more divergent thinking yet still boosts final outcomes compared to a no-AI control. Labeling amplifies both subjective and objective adoption of AI ideas, although most participants could detect AI sources even when unlabeled. Furthermore, qualitative interviews highlight nuanced perspectives on perceived ownership, authenticity, and the ways in which labeling triggers deeper scrutiny of the AI’s style. By demonstrating that baseline creativity moderates these effects more robustly than trust in AI, this study advances our theoretical understanding of multi-round human–AI synergy while offering design guidelines for next-generation creativity support systems. We discuss how user-centered design can balance rapid convergence (via early AI) with strategic pivot opportunities (via late AI) and weigh transparent labeling against ethical considerations of authorship and user autonomy.

Carter Blair, Kate Larson, Edith Law

AI agents are commonly aligned with "human values" through reinforcement learning from human feedback (RLHF), where a single reward model is learned from aggregated human feedback and used to align an agent's behavior. However, human values are not homogeneous--different people hold distinct and sometimes conflicting values. Aggregating feedback into a single reward model risks disproportionately suppressing minority preferences. To address this, we present a novel reward modeling approach for learning individualized reward models. Our approach uses a language model to guide users through reflective dialogues where they critique agent behavior and construct their preferences. This personalized dialogue history, containing the user's reflections and critiqued examples, is then used as context for another language model that serves as an individualized reward function (what we call a "verbal reward model") for evaluating new trajectories. In studies with 30 participants, our method achieved a 9-12% improvement in accuracy over non-reflective verbal reward models while being more sample efficient than traditional supervised learning methods.