Research Papers

Reliable uncertainty quantification is critical for trustworthy AI. Conformal Prediction (CP) provides prediction sets with distribution-free coverage guarantees, but its two main variants face complementary limitations. Split CP (SCP) suffers from data inefficiency due to dataset partitioning, while full CP (FCP) improves data efficiency at the cost of prohibitive retraining complexity. Recent approaches based on meta-learning or in-context learning (ICL) partially mitigate these drawbacks. However, they rely on training procedures not specifically tailored to CP, which may yield large prediction sets. We introduce an efficient FCP framework, termed enhanced ICL-based FCP (E-ICL+FCP), which employs a permutation-invariant Transformer-based ICL model trained with a CP-aware loss. By simulating the multiple retrained models required by FCP without actual retraining, E-ICL+FCP preserves coverage while markedly reducing both inefficiency and computational overhead. Experiments on synthetic and real tasks demonstrate that E-ICL+FCP attains superior efficiency-coverage trade-offs compared to existing SCP and FCP baselines.

As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted significant societal and regulatory concerns. In response, governments have issued ethics guidelines to promote the development of trustworthy AI. However, these guidelines are typically high-level demands for developers and testers, leaving a gap in translating them into actionable testing questions to verify LLM compliance. To address this challenge, we introduce GUARD (Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics), a testing method designed to operationalize guidelines into specific guideline-violating questions that assess LLM adherence. To implement this, GUARD uses automated generation of guideline-violating questions based on government-issued guidelines, thereby testing whether responses comply with these guidelines. When responses directly violate guidelines, GUARD reports inconsistencies. Furthermore, for responses that do not directly violate guidelines, GUARD integrates the concept of ``jailbreaks'' to diagnostics, named GUARD-JD, which creates scenarios that provoke unethical or guideline-violating responses, effectively identifying potential scenarios that could bypass built-in safety mechanisms. Our method finally culminates in a compliance report, delineating the extent of adherence and highlighting any violations. We empirically validated the effectiveness of GUARD on eight LLMs, including Vicuna-13B, LongChat-7B, Llama2-7B, Llama-3-8B, GPT-3.5, GPT-4, GPT-4o, and Claude-3.7, by testing compliance under three government-issued guidelines and conducting jailbreak diagnostics. Additionally, GUARD-JD can transfer jailbreak diagnostics to vision-language models (MiniGPT-v2 and Gemini-1.5), demonstrating its usage in promoting reliable LLM-based applications.

Language Models Identify Ambiguities and Exploit Loopholes

Jio Choi, Mohit Bansal, Elias Stengel-Eskin

Studying the responses of large language models (LLMs) to loopholes presents a two-fold opportunity. First, it affords us a lens through which to examine ambiguity and pragmatics in LLMs, since exploiting a loophole requires identifying ambiguity and performing sophisticated pragmatic reasoning. Second, loopholes pose an interesting and novel alignment problem where the model is presented with conflicting goals and can exploit ambiguities to its own advantage. To address these questions, we design scenarios where LLMs are given a goal and an ambiguous user instruction in conflict with the goal, with scenarios covering scalar implicature, structural ambiguities, and power dynamics. We then measure different models' abilities to exploit loopholes to satisfy their given goals as opposed to the goals of the user. We find that both closed-source and stronger open-source models can identify ambiguities and exploit their resulting loopholes, presenting a potential AI safety risk. Our analysis indicates that models which exploit loopholes explicitly identify and reason about both ambiguity and conflicting goals.

This paper introduces a novel approach to tackle the challenges of preserving and transferring tacit knowledge--deep, experience-based insights that are hard to articulate but vital for decision-making, innovation, and problem-solving. Traditional methods rely heavily on human facilitators, which, while effective, are resource-intensive and lack scalability. A promising alternative is the use of Socially Interactive Agents (SIAs) as AI-driven knowledge transfer facilitators. These agents interact autonomously and socially intelligently with users through multimodal behaviors (verbal, paraverbal, nonverbal), simulating expert roles in various organizational contexts. SIAs engage employees in empathic, natural-language dialogues, helping them externalize insights that might otherwise remain unspoken. Their success hinges on building trust, as employees are often hesitant to share tacit knowledge without assurance of confidentiality and appreciation. Key technologies include Large Language Models (LLMs) for generating context-relevant dialogue, Retrieval-Augmented Generation (RAG) to integrate organizational knowledge, and Chain-of-Thought (CoT) prompting to guide structured reflection. These enable SIAs to actively elicit knowledge, uncover implicit assumptions, and connect insights to broader organizational contexts. Potential applications span onboarding, where SIAs support personalized guidance and introductions, and knowledge retention, where they conduct structured interviews with retiring experts to capture heuristics behind decisions. Success depends on addressing ethical and operational challenges such as data privacy, algorithmic bias, and resistance to AI. Transparency, robust validation, and a culture of trust are essential to mitigate these risks.

RelAItionship Building: Analyzing Recruitment Strategies for Participatory AI

Eugene Kim, Vaibhav Balloli, Berelian Karimian +2

Participatory AI, in which impacted community members and other stakeholders are involved in the design and development of AI systems, holds promise as a way to ensure AI is developed to meet their needs and reflect their values. However, the process of identifying, reaching out, and engaging with all relevant stakeholder groups, which we refer to as recruitment methodology, is still a practical challenge in AI projects striving to adopt participatory practices. In this paper, we investigate the challenges that researchers face when designing and executing recruitment methodology for Participatory AI projects, and the implications of current recruitment practice for Participatory AI. First, we describe the recruitment methodologies used in AI projects using a corpus of 37 projects to capture the diversity of practices in the field and perform an initial analysis on the documentation of recruitment practices, as well as specific strategies that researchers use to meet goals of equity and empowerment. To complement this analysis, we interview five AI researchers to learn about the outcomes of recruitment methodologies. We find that these outcomes are shaped by structural conditions of their work, researchers' own goals and expectations, and the relationships built from the recruitment methodology and subsequent collaboration. Based on these analyses, we provide recommendations for designing and executing relationship-forward recruitment methods, as well as reflexive recruitment documentation practices for Participatory AI researchers.

The rapid adoption of large language models (LLMs) in customer service introduces new risks, as malicious actors can exploit them to conduct large-scale user impersonation through machine-generated text (MGT). Current MGT detection methods often struggle in online conversational settings, reducing the reliability and interpretability essential for trustworthy AI deployment. In customer service scenarios where operators are typically non-expert users, explanation become crucial for trustworthy MGT detection. In this paper, we propose EMMM, an explanation-then-detection framework that balances latency, accuracy, and non-expert-oriented interpretability. Experimental results demonstrate that EMMM provides explanations accessible to non-expert users, with 70\% of human evaluators preferring its outputs, while achieving competitive accuracy compared to state-of-the-art models and maintaining low latency, generating outputs within 1 second. Our code and dataset are open-sourced at https://github.com/AngieYYF/EMMM-explainable-chatbot-detection.

People's experiences of discrimination are often shaped by multiple intersecting factors, yet algorithmic fairness research rarely reflects this complexity. While intersectionality offers tools for understanding how forms of oppression interact, current approaches to intersectional algorithmic fairness tend to focus on narrowly defined demographic subgroups. These methods contribute important insights but risk oversimplifying social reality and neglecting structural inequalities. In this paper, we outline how a substantive approach to intersectional algorithmic fairness can reorient this research and practice. In particular, we propose Substantive Intersectional Algorithmic Fairness, extending Green's (2022) notion of substantive algorithmic fairness with insights from intersectional feminist theory. Aiming to provide as actionable guidance as possible, our approach is articulated as ten desiderata to guide the design, assessment, and deployment of algorithmic systems that address systemic inequities while mitigating harms to intersectionally marginalized communities. Rather than prescribing fixed operationalizations, these desiderata invite AI practitioners and experts to reflect on assumptions of neutrality, the use of protected attributes, the inclusion of multiply marginalized groups, and the transformative potential of algorithmic systems. By bridging computational and social science perspectives, the approach emphasizes that fairness cannot be separated from social context, and that in some cases, principled non-deployment may be necessary.

The growing adoption of home banking systems has increased cyberfraud risks, requiring detection models that are accurate, fair, and explainable. While AI methods show promise, they face challenges including computational inefficiency, limited interpretability of spiking neural networks (SNNs), and instability in reinforcement learning (RL)-based hyperparameter optimization. We propose a framework combining a Cortical Spiking Network with Population Coding (CSNPC) and a Reinforcement-Guided Hyper-Heuristic Optimizer (RHOSS). CSNPC leverages population coding for robust classification, while RHOSS applies Q-learning to adaptively select low-level heuristics under fairness and recall constraints. Integrated within the MoSSTI framework, the system incorporates explainable AI via saliency maps and spike activity profiling. Evaluated on the Bank Account Fraud (BAF) dataset, the model achieves 90.8% recall at 5% false positive rate, outperforming prior spiking and classical models while maintaining over 98% predictive equality across demographic groups. Although RHOSS introduces offline optimization cost, it is amortized at deployment. The sparse architecture of CSNPC further reduces energy consumption compared to dense ANNs. Results demonstrate that combining population-coded SNNs with RL-guided hyper-heuristics enables fair, interpretable, and high-performance fraud detection.

Understanding the factors that shape students' mathematics performance is vital for designing effective educational policies. This study applies explainable artificial intelligence (XAI) techniques to PISA 2018 data to predict math achievement and identify key predictors across ten countries (67,329 students). We tested four models: Multiple Linear Regression (MLR), Random Forest (RF), CATBoost, and Artificial Neural Networks (ANN), using student, family, and school variables. Models were trained on 70% of the data (with 5-fold cross-validation) and tested on 30%, stratified by country. Performance was assessed with R^2 and Mean Absolute Error (MAE). To ensure interpretability, we used feature importance, SHAP values, and decision tree visualizations. Non-linear models, especially RF and ANN, outperformed MLR, with RF balancing accuracy and generalizability. Key predictors included socio-economic status, study time, teacher motivation, and students' attitudes toward mathematics, though their impact varied across countries. Visual diagnostics such as scatterplots of predicted vs actual scores showed RF and CATBoost aligned closely with actual performance. Findings highlight the non-linear and context-dependent nature of achievement and the value of XAI in educational research. This study uncovers cross-national patterns, informs equity-focused reforms, and supports the development of personalized learning strategies.

The rapid proliferation of Generative AI (GenAI) into diverse, high-stakes domains necessitates robust and reproducible evaluation methods. However, practitioners often resort to ad-hoc, non-standardized scripts, as common metrics are often unsuitable for specialized, structured outputs (e.g., automated plans, time-series) or holistic comparison across modalities (e.g., text, audio, and image). This fragmentation hinders comparability and slows AI system development. To address this challenge, we present GAICo (Generative AI Comparator): a deployed, open-source Python library that streamlines and standardizes GenAI output comparison. GAICo provides a unified, extensible framework supporting a comprehensive suite of reference-based metrics for unstructured text, specialized structured data formats, and multimedia (images, audio). Its architecture features a high-level API for rapid, end-to-end analysis, from multi-model comparison to visualization and reporting, alongside direct metric access for granular control. We demonstrate GAICo's utility through a detailed case study evaluating and debugging complex, multi-modal AI Travel Assistant pipelines. GAICo empowers AI researchers and developers to efficiently assess system performance, make evaluation reproducible, improve development velocity, and ultimately build more trustworthy AI systems, aligning with the goal of moving faster and safer in AI deployment. Since its release on PyPI in Jun 2025, the tool has been downloaded over 16K times, across versions, by Dec 2025, demonstrating growing community interest.

This paper proposes an eXplainable Artificial Intelligence (XAI)-driven methodology to enhance the understanding of cough sound analysis for respiratory disease management. We employ occlusion maps to highlight relevant spectral regions in cough spectrograms processed by a Convolutional Neural Network (CNN). Subsequently, spectral analysis of spectrograms weighted by these occlusion maps reveals significant differences between disease groups, particularly in patients with COPD, where cough patterns appear more variable in the identified spectral regions of interest. This contrasts with the lack of significant differences observed when analyzing raw spectrograms. The proposed approach extracts and analyzes several spectral features, demonstrating the potential of XAI techniques to uncover disease-specific acoustic signatures and improve the diagnostic capabilities of cough sound analysis by providing more interpretable results.

Explainable Artificial Intelligence (XAI) methods, such as Local Interpretable Model-Agnostic Explanations (LIME), have advanced the interpretability of black-box machine learning models by approximating their behavior locally using interpretable surrogate models. However, LIME's inherent randomness in perturbation and sampling can lead to locality and instability issues, especially in scenarios with limited training data. In such cases, data scarcity can result in the generation of unrealistic variations and samples that deviate from the true data manifold. Consequently, the surrogate model may fail to accurately approximate the complex decision boundary of the original model. To address these challenges, we propose a novel Instance-based Transfer Learning LIME framework (ITL-LIME) that enhances explanation fidelity and stability in data-constrained environments. ITL-LIME introduces instance transfer learning into the LIME framework by leveraging relevant real instances from a related source domain to aid the explanation process in the target domain. Specifically, we employ clustering to partition the source domain into clusters with representative prototypes. Instead of generating random perturbations, our method retrieves pertinent real source instances from the source cluster whose prototype is most similar to the target instance. These are then combined with the target instance's neighboring real instances. To define a compact locality, we further construct a contrastive learning-based encoder as a weighting mechanism to assign weights to the instances from the combined set based on their proximity to the target instance. Finally, these weighted source and target instances are used to train the surrogate model for explanation purposes.