Mallika Mainali

Mallika Mainali, Rosina O Weber

We often see the term explainable in the titles of papers that describe applications based on artificial intelligence (AI). However, the literature in explainable artificial intelligence (XAI) indicates that explanations in XAI are application- and domain-specific, hence requiring evaluation whenever they are employed to explain a model that makes decisions for a specific application problem. Additionally, the literature reveals that the performance of post-hoc methods, particularly feature attribution methods, varies substantially hinting that they do not represent a solution to AI explainability. Therefore, when using XAI methods, the quality and suitability of their information outputs should be evaluated within the specific application. For these reasons, we used a scoping review methodology to investigate papers that apply AI models and adopt methods to generate post-hoc explanations while referring to said models as explainable. This paper investigates whether the term explainable model is adopted by authors under the assumption that incorporating a post-hoc XAI method suffices to characterize a model as explainable. To inspect this problem, our review analyzes whether these papers conducted evaluations. We found that 81% of the application papers that refer to their approaches as an explainable model do not conduct any form of evaluation on the XAI method they used.

Mallika Mainali, Harsha Sureshbabu, Anik Sen et al.

As algorithmic decision-makers are increasingly applied to high-stakes domains, AI alignment research has evolved from a focus on universal value alignment to context-specific approaches that account for decision-maker attributes. Prior work on Decision-Maker Alignment (DMA) has explored two primary strategies: (1) classical AI methods integrating case-based reasoning, Bayesian reasoning, and naturalistic decision-making, and (2) large language model (LLM)-based methods leveraging prompt engineering. While both approaches have shown promise in limited domains such as medical triage, their generalizability to novel contexts remains underexplored. In this work, we implement a prior classical AI model and develop an LLM-based algorithmic decision-maker evaluated using a large reasoning model (GPT-5) and a non-reasoning model (GPT-4) with weighted self-consistency under a zero-shot prompting framework, as proposed in recent literature. We evaluate both approaches on a health insurance decision-making dataset annotated for three target decision-makers with varying levels of risk tolerance (0.0, 0.5, 1.0). In the experiments reported herein, classical AI and LLM-based models achieved comparable alignment with attribute-based targets, with classical AI exhibiting slightly better alignment for a moderate risk profile. The dataset and open-source implementation are publicly available at: https://github.com/TeX-Base/ClassicalAIvsLLMsforDMAlignment and https://github.com/Parallax-Advanced-Research/ITM/tree/feature_insurance.

Ximing Wen, Mallika Mainali, Anik Sen

Vision Language Models (VLMs) have demonstrated strong reasoning capabilities in Visual Question Answering (VQA) tasks; however, their ability to perform Theory of Mind (ToM) tasks, such as inferring human intentions, beliefs, and mental states, remains underexplored. We propose an open-ended question framework to evaluate VLMs' performance across diverse categories of ToM tasks. We curated and annotated a benchmark dataset of 30 images and evaluated the performance of four VLMs of varying sizes. Our results show that the GPT-4 model outperformed all the others, with only one smaller model, GPT-4o-mini, achieving comparable performance. We observed that VLMs often struggle to infer intentions in complex scenarios such as bullying or cheating. Our findings reveal that smaller models can sometimes infer correct intentions despite relying on incorrect visual cues. The dataset is available at https://github.com/ximingwen/ToM-AAAI25-Multimodal.

Mallika Mainali, Rosina O. Weber

Cognitive attributes are fundamental to metacognition, shaping how individuals process information, evaluate choices, and make decisions. To develop metacognitive artificial intelligence (AI) models that reflect human reasoning, it is essential to account for the attributes that influence reasoning patterns and decision-maker behavior, often leading to different or even conflicting choices. This makes it crucial to incorporate cognitive attributes in designing AI models that align with human decision-making processes, especially in high-stakes domains such as finance, where decisions have significant real-world consequences. However, existing AI alignment research has primarily focused on value alignment, often overlooking the role of individual cognitive attributes that distinguish decision-makers. To address this issue, this paper (1) analyzes the literature on cognitive attributes, (2) establishes five criteria for defining them, and (3) categorizes 19 domain-specific cognitive attributes relevant to financial decision-making. These three components provide a strong basis for developing AI systems that accurately reflect and align with human decision-making processes in financial contexts.

Mouad Abrini, Omri Abend, Dina Acklin et al. · cambridge

This volume includes a selection of papers presented at the Workshop on Advancing Artificial Intelligence through Theory of Mind held at AAAI 2025 in Philadelphia US on 3rd March 2025. The purpose of this volume is to provide an open access and curated anthology for the ToM and AI research community.