Related papers: Reasoning as Data: Representation-Computation Unit…
The mathematical framework of Stone duality is used to synthesize a number of hitherto separate developments in Theoretical Computer Science: - Domain Theory, the mathematical theory of computation introduced by Scott as a foundation for…
While enterprises amass vast quantities of data, much of it remains chaotic and effectively dormant, preventing decision-making based on comprehensive information. Existing neuro-symbolic approaches rely on disjoint pipelines and struggle…
We present DART, an open domain structured DAta Record to Text generation dataset with over 82k instances (DARTs). Data-to-Text annotations can be a costly process, especially when dealing with tables which are the major source of…
Chain-of-Thought (CoT) prompting significantly improves reasoning in Large Language Models, yet the temporal dynamics of the underlying representation geometry remain poorly understood. We investigate these dynamics by applying Manifold…
Recent advances in machine learning have led to a surge in adoption of neural networks for various tasks, but lack of interpretability remains an issue for many others in which an understanding of the features influencing the prediction is…
Document interpretation and dialog understanding are the two major challenges for conversational machine reading. In this work, we propose Discern, a discourse-aware entailment reasoning network to strengthen the connection and enhance the…
Sentential Calculus with Identity (SCI) is an extension of classical propositional logic, featuring a new connective of identity between formulas. In SCI two formulas are said to be identical if they share the same denotation. In the…
Chain-of-thought (CoT) prompting improves LLM reasoning but incurs high latency and memory cost due to verbose traces, motivating CoT compression with preserved correctness. Existing methods either shorten CoTs at the semantic level, which…
Recent cross-domain recommendation (CDR) studies assume that disentangled domain-shared and domain-specific user representations can mitigate domain gaps and facilitate effective knowledge transfer. However, achieving perfect…
Tabular documents such as CSV and Excel files are widely used in enterprise data pipelines, yet existing chunking strategies for retrieval-augmented generation (RAG) are primarily designed for unstructured text and do not account for…
Knowledge is the most precious asset of humankind. People extract the experience from the data that provide for us the reality through the feelings. Generally speaking, it is possible to see the analogy of knowledge elaboration between…
Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial…
While AI innovation accelerates rapidly, the intellectual process behind breakthroughs -- how researchers identify gaps, synthesize prior work, and generate insights -- remains poorly understood. The lack of structured data on scientific…
For argumentation mining, there are several sub-tasks such as argumentation component type classification, relation classification. Existing research tends to solve such sub-tasks separately, but ignore the close relation between them. In…
Datalog reasoning based on the semina\"ive evaluation strategy evaluates rules using traditional join plans, which often leads to redundancy and inefficiency in practice, especially when the rules are complex. Hypertree decompositions help…
Learning generic and robust feature representations with data from multiple domains for the same problem is of great value, especially for the problems that have multiple datasets but none of them are large enough to provide abundant data…
Contextual clinical reasoning demands robust inference grounded in complex, heterogeneous clinical records. While state-of-the-art fine-tuning, in-context learning (ICL), and retrieval-augmented generation (RAG) enable knowledge exposure,…
Despite the superior performance of Large Reasoning Models (LRMs), their reasoning behaviors are often counterintuitive, leading to suboptimal reasoning capabilities. To theoretically formalize the desired reasoning behaviors, this paper…
In this paper, an application of automated theorem proving techniques to computational semantics is considered. In order to compute the presuppositions of a natural language discourse, several inference tasks arise. Instead of treating…
As Large Language Models (LLMs) evolve into persistent scientific collaborators, context window saturation has emerged as a critical bottleneck. Scientific workflows involving iterative data analysis and hypothesis refinement rapidly…