Related papers: UniRPG: Unified Discrete Reasoning over Table and …
Structured tabular data is a fundamental data type in numerous fields, and the capacity to reason over tables is crucial for answering questions and validating hypotheses. However, constructing labeled data for complex reasoning tasks is…
Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address…
Tables convey factual and quantitative data with implicit conventions created by humans that are often challenging for machines to parse. Prior work on table recognition (TR) has mainly centered around complex task-specific combinations of…
Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are…
Abstract visual reasoning (AVR) enables humans to quickly discover and generalize abstract rules to new scenarios. Designing intelligent systems with human-like AVR abilities has been a long-standing topic in the artificial intelligence…
Retrieval-Augmented Generation (RAG) has demonstrated considerable effectiveness in open-domain question answering. However, when applied to heterogeneous documents, comprising both textual and tabular components, existing RAG approaches…
An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction. Ideally, rationale extraction should be faithful (reflective of LM's actual…
In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions. Describing scientific tables goes beyond…
Retrieval-Augmented Generation (RAG) enhances the reasoning ability of Large Language Models (LLMs) by dynamically integrating external knowledge, thereby mitigating hallucinations and strengthening contextual grounding for structured data…
How can we perform computations over natural language representations to solve tasks that require symbolic and numeric reasoning? We propose natural language embedded programs (NLEP) as a unifying framework for addressing math/symbolic…
Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions (NLQs) by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods either rely on employing…
Incorporating external knowledge bases in traditional retrieval-augmented generation (RAG) relies on parsing the document, followed by querying a language model with the parsed information via in-context learning. While effective for…
Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent…
Discrete mathematics is the foundation of computer science. It focuses on concepts and reasoning methods that are studied using math notations. It has long been argued that discrete math is better taught with programming, which takes…
Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous information, and the types of reasoning are mainly divided into numerical reasoning and span extraction. Current numerical reasoning methods…
Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to answer a question,…
We present a novel Dynamic Differentiable Reasoning (DDR) framework for jointly learning branching programs and the functions composing them; this resolves a significant nondifferentiability inhibiting recent dynamic architectures. We apply…
Test-time scaling has emerged as an effective way to improve language models on challenging reasoning tasks. However, most existing methods treat each problem in isolation and do not systematically reuse knowledge from prior reasoning…
Retrieval-Augmented Generation (RAG) has become a standard approach for knowledge-intensive question answering, but existing systems remain brittle on multi-hop questions, where solving the task requires chaining multiple retrieval and…
A growing body of research suggests that the cognitive processes of large language models (LLMs) differ fundamentally from those of humans. However, existing interpretability methods remain limited in explaining how cognitive abilities are…