Related papers: STRIDE: Strategic Iterative Decision-Making for Re…

Open-domain question answering over datalakes requires retrieving and composing information from multiple tables, a challenging subtask that demands semantic relevance and structural coherence (e.g., joinability). While exact optimization…

Current temporal knowledge graph question answering (TKGQA) methods primarily focus on implicit temporal constraints, lacking the capability of handling more complex temporal queries, and struggle with limited reasoning abilities and error…

Existing approaches for open-domain question answering (QA) are typically designed for questions that require either single-hop or multi-hop reasoning, which make strong assumptions of the complexity of questions to be answered. Also,…

In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer. Recently, dense retrieval also achieved state-of-the-art results in multi-hop…

Recent advances in Large Language Models (LLMs) have significantly improved table understanding tasks such as Table Question Answering (TableQA), yet challenges remain in ensuring reliability, scalability, and efficiency, especially in…

Multimodal Stance Detection (MSD) is a crucial task for understanding public opinion on social media. Existing methods predominantly operate by learning to fuse modalities. They lack an explicit reasoning process to discern how inter-modal…

Answering numerical questions over hybrid contents from the given tables and text(TextTableQA) is a challenging task. Recently, Large Language Models (LLMs) have gained significant attention in the NLP community. With the emergence of large…

The semantic parsing-based method is an important research branch for knowledge-based question answering. It usually generates executable programs lean upon the question and then conduct them to reason answers over a knowledge base. Benefit…

Recent advancements in language agents have led to significant improvements in multi-hop reasoning tasks. However, existing approaches often struggle with handling open-domain problems, which require massive information retrieval due to…

Multi-stage reasoning has emerged as an effective strategy for enhancing the reasoning capability of small language models by decomposing complex problems into sequential sub-stages. However, this comes at the cost of increased latency. We…

Question answering (QA) over tables and linked text, also called TextTableQA, has witnessed significant research in recent years, as tables are often found embedded in documents along with related text. HybridQA and OTT-QA are the two…

Retrieval-augmented Large Language Models (LLMs) have reshaped traditional query-answering systems, offering unparalleled user experiences. However, existing retrieval techniques often struggle to handle multi-modal query contexts. In this…

Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A fundamental challenge lies in efficiently identifying the minimal relevant document set…

Knowledge Graph Question Answering aims to answer natural language questions by reasoning over structured knowledge graphs. While large language models have advanced KGQA through their strong reasoning capabilities, existing methods…

Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-step dependencies, which presents substantial challenges for…

Generating high-quality MCQs, especially those targeting diverse cognitive levels and incorporating common misconceptions into distractor design, is time-consuming and expertise-intensive, making manual creation impractical at scale.…

Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H$ attention heads produce exactly $H$ independent attention…

Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-reasoning loops meaningfully outperform static RAG, particularly in scientific domains with…

Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams. We argue that the explainability of this task should place…

Multi-step reasoning remains a key challenge for Large Language Models (LLMs), particularly in complex domains such as mathematics and creative writing. While recent approaches including ReAct, Reflexion, and Self-Refine improve reasoning…