Related papers: Reinforcement Learning Enhanced Multi-hop Reasonin…

Long Chain-of-Thought (LCoT), achieved by Reinforcement Learning with Verifiable Rewards (RLVR), has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs). However, reasoning in current LLMs is primarily…

Question Answering over Knowledge Graph (KGQA) aims to seek answer entities for the natural language question from a large-scale Knowledge Graph~(KG). To better perform reasoning on KG, recent work typically adopts a pre-trained language…

A Temporal Knowledge Graph (TKG) is a sequence of KGs with respective timestamps, which adopts quadruples in the form of (\emph{subject}, \emph{relation}, \emph{object}, \emph{timestamp}) to describe dynamic facts. TKG reasoning has…

Optimizing communication topology is fundamental to the efficiency and effectiveness of Large Language Model (LLM)-based Multi-Agent Systems (MAS). While recent approaches utilize reinforcement learning to dynamically construct…

Multi-hop reading comprehension (MHRC) requires not only to predict the correct answer span in the given passage, but also to provide a chain of supporting evidences for reasoning interpretability. It is natural to model such a process into…

Accurately answering complex questions has consistently been a significant challenge for Large Language Models (LLMs). To address this, this paper proposes a multi-hop question decomposition method for complex questions, building upon…

Multimodal Object-Entity Relation Extraction (MORE) is a challenging task in information extraction research. It aims to identify relations between visual objects and textual entities, requiring complex multimodal understanding and…

Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…

Large Language Models (LLMs) have recently demonstrated remarkable reasoning abilities, yet hallucinate on knowledge-intensive tasks. Retrieval-augmented generation (RAG) mitigates this issue by grounding answers in external sources, e.g.,…

Multi-hop reasoning has been widely studied in recent years to seek an effective and interpretable method for knowledge graph (KG) completion. Most previous reasoning methods are designed for dense KGs with enough paths between entities,…

Understanding temporal relations and answering time-sensitive questions is crucial yet a challenging task for question-answering systems powered by large language models (LLMs). Existing approaches either update the parametric knowledge of…

Temporal Knowledge Graph (TKG) completion models traditionally assume access to the entire graph during training. This overlooks challenges stemming from the evolving nature of TKGs, such as: (i) the model's requirement to generalize and…

Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based…

Temporal Knowledge Graph (TKG) reasoning involves predicting future events based on historical information. However, due to the unpredictability of future events, this task is highly challenging. To address this issue, we propose a…

Recent advancements in large language models (LLMs) and multi-modal LLMs have been remarkable. However, these models still rely solely on their parametric knowledge, which limits their ability to generate up-to-date information and…

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…

Reinforcement learning (RL) based on the final answer's reward has driven recent progress in small language models (SLMs) on reasoning-heavy tasks such as math and code. However, applying the same techniques to retrieval-augmented…

Long-context question-answering (LCQA) systems have greatly benefited from the powerful reasoning capabilities of large language models (LLMs), which can be categorized into slow and quick reasoning modes. However, both modes have their…

Test-time augmentation, such as Retrieval-Augmented Generation (RAG) or tool use, critically depends on an interplay between a model's parametric knowledge and externally retrieved information. However, the theoretical underpinnings of this…

Modern systems for multi-hop question answering (QA) typically break questions into a sequence of reasoning steps, termed chain-of-thought (CoT), before arriving at a final answer. Often, multiple chains are sampled and aggregated through a…