相关论文: Shadow-Loom: Causal Reasoning over Graphical World…

We introduce CHARTOM, a visual theory-of-mind benchmark designed to evaluate multimodal large language models' capability to understand and reason about misleading data visualizations though charts. CHARTOM consists of carefully designed…

Large Vision-Language Models (LVLMs) represent a significant leap towards empathetic agents, demonstrating remarkable capabilities in emotion understanding. However, the internal mechanisms governing how LVLMs translate abstract visual…

A Random Graph is a random object which take its values in the space of graphs. We take advantage of the expressibility of graphs in order to model the uncertainty about the existence of causal relationships within a given set of variables.…

Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample…

Generative AI has established the opportunity to readily transform content from one medium to another. This capability is especially powerful for storytelling, where visual illustrations can illuminate a story originally expressed in text.…

We introduce CausaLab, a scalable environment for evaluating interactive causal discovery by LLM agents. Unlike prior evaluations, CausaLab evaluates both whether an agent can solve a problem using causal evidence and whether its answer is…

Large language models have shown astonishing performance on a wide range of reasoning tasks. In this paper, we investigate whether they could reason about real-world events and help improve the prediction performance of event sequence…

World models improve a learning agent's ability to efficiently operate in interactive and situated environments. This work focuses on the task of building world models of text-based game environments. Text-based games, or interactive…

Pre-trained sequence-to-sequence language models have led to widespread success in many natural language generation tasks. However, there has been relatively less work on analyzing their ability to generate structured outputs such as…

Reasoning, a crucial aspect of NLP research, has not been adequately addressed by prevailing models including Large Language Model. Conversation reasoning, as a critical component of it, remains largely unexplored due to the absence of a…

Media narratives wield tremendous power in shaping public opinion, yet computational approaches struggle to capture the nuanced storytelling structures that communication theory emphasizes as central to how meaning is constructed. Existing…

Trajectory modeling refers to characterizing human movement behavior, serving as a pivotal step in understanding mobility patterns. Nevertheless, existing studies typically ignore the confounding effects of geospatial context, leading to…

Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and evaluation pipelines. Here, we argue that many central questions in LLM development and…

Counterfactual thinking is a crucial yet challenging topic for artificial intelligence to learn knowledge from data and ultimately improve performance for new scenarios. Many research works, including the Potential Outcome Model (POM) and…

Probabilistic sentential decision diagrams are a class of structured-decomposable probabilistic circuits especially designed to embed logical constraints. To adapt the classical LearnSPN scheme to learn the structure of these models, we…

Stories interest us not because they are a sequence of mundane and predictable events but because they have drama and tension. Crucial to creating dramatic and exciting stories are surprise and suspense. The thesis trains a series of deep…

Large Language Models (LLMs) leverage chain-of-thought (CoT) prompting to provide step-by-step rationales, improving performance on complex tasks. Despite its benefits, vanilla CoT often fails to fully verify intermediate inferences and can…

Structural causal models postulate noisy functional relations among a set of interacting variables. The causal structure underlying each such model is naturally represented by a directed graph whose edges indicate for each variable which…

Large language models (LLMs) have shown great potential in decision-making due to the vast amount of knowledge stored within the models. However, these pre-trained models are prone to lack reasoning abilities and are difficult to adapt to…

The representations of the world around in physics built with help of causality are analyzed and seems incomplete. The observer's causal representations form a closed logical system, i.e. the compact group related to cause-effect chains.…