Related papers: UniRPG: Unified Discrete Reasoning over Table and …

Recent multimodal large language models (MLLMs) still struggle with long document understanding due to two fundamental challenges: information interference from abundant irrelevant content, and the quadratic computational cost of…

Recent advancements in NLP have witnessed the groundbreaking impact of pretrained models, yielding impressive outcomes across various tasks. This study seeks to extend the power of pretraining methodologies to facilitating the prediction…

Deployed language models must decide not only what to answer but also when not to answer. We present UniCR, a unified framework that turns heterogeneous uncertainty evidence including sequence likelihoods, self-consistency dispersion,…

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding responses in external knowledge during inference. However, conventiona RAG systems under-perform on structured tabular data, largely due to coarse…

Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models. In this paper, we present an approach that reasons about complex questions by decomposing them to…

Existing medical RAG systems mainly leverage knowledge from medical knowledge bases, neglecting the crucial role of experiential knowledge derived from similar patient cases -- a key component of human clinical reasoning. To bridge this…

In AI-facilitated teaching, leveraging various query styles to interpret abstract educational content is crucial for delivering effective and accessible learning experiences. However, existing retrieval systems predominantly focus on…

Tabular data serves as the backbone of modern data analysis and scientific research. While Large Language Models (LLMs) fine-tuned via Supervised Fine-Tuning (SFT) have significantly improved natural language interaction with such…

Programming with logic for sophisticated applications must deal with recursion and negation, which together have created significant challenges in logic, leading to many different, conflicting semantics of rules. This paper describes a…

Large Language Models excel at code generation yet struggle with complex programming tasks that demand sophisticated reasoning. To bridge this gap, traditional process supervision relies on learned reward models requiring costly training…

Multimodal large language models are increasingly expected to perform thinking with images, yet existing visual latent reasoning methods still rely on explicit textual chain-of-thought interleaved with visual latent tokens. This interleaved…

Graph Retrieval-Augmented Generation (Graph RAG) effectively builds a knowledge graph (KG) to connect disparate facts across a large document corpus. However, this broad-view approach often lacks the deep structured reasoning needed for…

The widespread application of pre-trained language models (PLMs) in natural language processing (NLP) has led to increasing concerns about their explainability. Selective rationalization is a self-explanatory framework that selects…

Answering visual queries is a complex task that requires both visual processing and reasoning. End-to-end models, the dominant approach for this task, do not explicitly differentiate between the two, limiting interpretability and…

Text-to-image generation has advanced rapidly with diffusion models, progressing from CLIP and T5 conditioning to unified systems where a single LLM backbone handles both visual understanding and generation. Despite the architectural…

Automated predictions require explanations to be interpretable by humans. One type of explanation is a rationale, i.e., a selection of input features such as relevant text snippets from which the model computes the outcome. However, a…

Many real world domains require the representation of a measure of uncertainty. The most common such representation is probability, and the combination of probability with logic programs has given rise to the field of Probabilistic Logic…

Complex question answering (CQA) over raw text is a challenging task. A prominent approach to this task is based on the programmer-interpreter framework, where the programmer maps the question into a sequence of reasoning actions which is…

Table Question Answering (TableQA) poses a significant challenge for large language models (LLMs) because conventional linearization of tables often disrupts the two-dimensional relationships intrinsic to structured data. Existing methods,…

Algorithmic reasoning refers to the ability to understand the complex patterns behind the problem and decompose them into a sequence of reasoning steps towards the solution. Such nature of algorithmic reasoning makes it a challenge for…