Related papers: Fact-driven Logical Reasoning for Machine Reading …

Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives. Prior work has largely tried to do this either symbolically or with black-box transformers. We present a middle ground…

State-of-the-art deep reading comprehension models are dominated by recurrent neural nets. Their sequential nature is a natural fit for language, but it also precludes parallelization within an instances and often becomes the bottleneck for…

Machine common sense remains a broad, potentially unbounded problem in artificial intelligence (AI). There is a wide range of strategies that can be employed to make progress on this challenge. This article deals with the aspects of…

With the continuous advancement of reasoning abilities in Large Language Models (LLMs), their application to scientific reasoning tasks has gained significant research attention. Current research primarily emphasizes boosting LLMs'…

Recent advancements in Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains. However, effective decision-making relies heavily on strong reasoning abilities. Reasoning is the foundation for…

Human learning thrives on the ability to learn from mistakes, adapt through feedback, and refine understanding-processes often missing in static machine learning models. In this work, we introduce Composite Learning Units (CLUs) designed to…

Deception detection has attracted increasing attention due to its importance in real-world scenarios. Its main goal is to detect deceptive behaviors from multimodal clues such as gestures, facial expressions, prosody, etc. However, these…

During the past few decades, knowledge bases (KBs) have experienced rapid growth. Nevertheless, most KBs still suffer from serious incompletion. Researchers proposed many tasks such as knowledge base completion and relation prediction to…

We focus on the task of reasoning over paragraph effects in situation, which requires a model to understand the cause and effect described in a background paragraph, and apply the knowledge to a novel situation. Existing works ignore the…

Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of isolated facts, often overlooking latent inferential…

Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can be answered. Although several recent…

Equipping machines with comprehensive knowledge of the world's entities and their relationships has been a long-standing goal of AI. Over the last decade, large-scale knowledge bases, also known as knowledge graphs, have been automatically…

Counterfactual explanations are gaining prominence within technical, legal, and business circles as a way to explain the decisions of a machine learning model. These explanations share a trait with the long-established "principal reason"…

Logical reasoning is central to complex human activities, such as thinking, debating, and planning; it is also a central component of many AI systems as well. In this paper, we investigate the extent to which encoder-only transformer…

Counterfactual reasoning has emerged as a crucial technique for generalizing the reasoning capabilities of large language models (LLMs). By generating and analyzing counterfactual scenarios, researchers can assess the adaptability and…

Evidence-based fact checking aims to verify the truthfulness of a claim against evidence extracted from textual sources. Learning a representation that effectively captures relations between a claim and evidence can be challenging. Recent…

The growing complexity of factual claims in real-world scenarios presents significant challenges for automated fact verification systems, particularly in accurately aggregating and reasoning over multi-hop evidence. Existing approaches…

Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning remain elusive. Recent reasoning models outperform comparable instruction-tuned models on complex cognitive tasks,…

Reading comprehension tasks test the ability of models to process long-term context and remember salient information. Recent work has shown that relatively simple neural methods such as the Attention Sum-Reader can perform well on these…

Large Language Models have demonstrated impressive reasoning capabilities across multiple languages. However, the relationship between capabilities in different languages is less explored. In this work, we decompose the process of reasoning…