Related papers: Controlling Search in Very large Commonsense Knowl…

Knowledge-based visual question answering (KB-VQA) is a challenging task, which requires the model to leverage external knowledge for comprehending and answering questions grounded in visual content. Recent studies retrieve the knowledge…

Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, where optimality improves with increased computational time.…

Large Language Models (LLMs) are often used as automated judges to evaluate text, but their effectiveness can be hindered by various unintentional biases. We propose using linear classifying probes, trained by leveraging differences between…

Large Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a reasoning trace before deriving the final answer. However, these extended generations incur substantial memory footprint and computational overhead,…

Knowledge bases (KB) constructed through information extraction from text play an important role in query answering and reasoning. In this work, we study a particular reasoning task, the problem of discovering causal relationships between…

Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations…

Question answering (QA) over knowledge bases (KBs) is challenging because of the diverse, essentially unbounded, types of reasoning patterns needed. However, we hypothesize in a large KB, reasoning patterns required to answer a query type…

We present the Open Predicate Query Language (OPQL); a method for constructing a virtual KB (VKB) trained entirely from text. Large Knowledge Bases (KBs) are indispensable for a wide-range of industry applications such as question answering…

Structured reasoning can improve the inference performance of large language models (LLMs), but it also introduces computational cost and control constraints. When additional reasoning structure helps, and when it instead reduces efficiency…

Recent Large Reasoning Models (LRMs), such as DeepSeek-R1 and OpenAI o1, have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference. However, a growing concern lies in their…

Large reasoning models (LRMs) substantially outperform their base LLM counterparts on challenging reasoning benchmarks, yet it remains poorly understood where base models go wrong during token-by-token generation and how to narrow this gap…

A common thread of retrieval-augmented methods in the existing literature focuses on retrieving encyclopedic knowledge, such as Wikipedia, which facilitates well-defined entity and relation spaces that can be modeled. However, applying such…

Temporal commonsense reasoning refers to the ability to understand the typical temporal context of phrases, actions, and events, and use it to reason over problems requiring such knowledge. This trait is essential in temporal natural…

Large knowledge bases (KBs) are useful for many AI tasks, but are difficult to integrate into modern gradient-based learning systems. Here we describe a framework for accessing soft symbolic database using only differentiable operators. For…

Decision tree induction systems are being used for knowledge acquisition in noisy domains. This paper develops a subjective Bayesian interpretation of the task tackled by these systems and the heuristic methods they use. It is argued that…

Knowledge graphs (KGs) provide information in machine interpretable form. In cases where multiple KGs are used in the same system, that information needs to be integrated. This is usually done by automated matching systems. Most of those…

Knowledge bases are collections of domain-specific and commonsense facts. Recently, the sizes of KBs are rocketing due to automatic extraction for knowledge and facts. For example, the number of facts in WikiData is up to 974 million!…

Knowledge Bases (KBs) contain a wealth of structured information about entities and predicates. This paper focuses on set-valued predicates, i.e., the relationship between an entity and a set of entities. In KBs, this information is often…

Smart premise selection is essential when using automated reasoning as a tool for large-theory formal proof development. A good method for premise selection in complex mathematical libraries is the application of machine learning to large…

Understanding narratives requires reading between the lines, which in turn, requires interpreting the likely causes and effects of events, even when they are not mentioned explicitly. In this paper, we introduce Cosmos QA, a large-scale…