Related papers: Distributed Partial Information Puzzles: Examining…

Group decision-making often suffers from uneven information sharing, hindering decision quality. While large language models (LLMs) have been widely studied as aids for individuals, their potential to support groups of users, potentially as…

Collaborative problem solving (CPS) enables student groups to complete learning tasks, construct knowledge, and solve problems. Previous research has argued the importance to examine the complexity of CPS, including its multimodality,…

Cognitive science often evaluates theories through narrow paradigms and local model comparisons, limiting the integration of evidence across tasks and realizations. We introduce an automated adversarial collaboration framework for…

This paper introduces the novel task of multimodal puzzle solving, framed within the context of visual question-answering. We present a new dataset, AlgoPuzzleVQA designed to challenge and evaluate the capabilities of multimodal language…

The proliferation of artificial intelligence provides an opportunity to create psychological spaciousness in society. Spaciousness is defined as the ability to hold diverse interpersonal interactions and forms the basis for vulnerability…

Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…

Mining large corpora can generate useful discoveries but is time-consuming for humans. We formulate a new task, D5, that automatically discovers differences between two large corpora in a goal-driven way. The task input is a problem…

In traditional Distributional Semantic Models (DSMs) the multiple senses of a polysemous word are conflated into a single vector space representation. In this work, we propose a DSM that learns multiple distributional representations of a…

This work introduces a novel deep learning-based architecture, termed the Deep Belief Markov Model (DBMM), which provides efficient, model-formulation agnostic inference in Partially Observable Markov Decision Process (POMDP) problems. The…

When agents collaborate on a task, it is important that they have some shared mental model of the task routines -- the set of feasible plans towards achieving the goals. However, in reality, situations often arise that such a shared mental…

In this paper, we investigate the use of large language models (LLMs) like ChatGPT for document-grounded response generation in the context of information-seeking dialogues. For evaluation, we use the MultiDoc2Dial corpus of task-oriented…

We investigate notions of ambiguity and partial information in categorical distributional models of natural language. Probabilistic ambiguity has previously been studied using Selinger's CPM construction. This construction works well for…

This paper presents SYMBIOSIS, an AI-powered framework and platform designed to make Systems Thinking accessible for addressing societal challenges and unlock paths for leveraging systems thinking frameworks to improve AI systems. The…

Dynamic Epistemic Logic (DEL) provides a framework for epistemic planning that is capable of representing non-deterministic actions, partial observability, higher-order knowledge and both factual and epistemic change. The high expressivity…

In human-agent teams, openly sharing goals is often assumed to enhance planning, collaboration, and effectiveness. However, direct communication of these goals is not always feasible, requiring teammates to infer their partner's intentions…

In this paper, we introduce Part-Aware Point Grounded Description (PaPGD), a challenging task aimed at advancing 3D multimodal learning for fine-grained, part-aware segmentation grounding and detailed explanation of 3D objects. Existing 3D…

Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal…

The aim of this paper is to investigate the interplay between knowledge shared by a group of agents and its coalition ability. We investigate this relation in the standard context of imperfect information concurrent game. We assume that…

Conversational AI has a fundamental flaw as a knowledge interface: sycophantic chatbots induce epistemic entrenchment and delusional belief spirals even in rational agents. We propose the problem does not stem from the AI model, rooted…

Grounding has been argued to be a crucial component towards the development of more complete and truly semantically competent artificial intelligence systems. Literature has divided into two camps: While some argue that grounding allows for…