Related papers: GRIP: A Graph-Based Reasoning Instruction Producer

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, including multi-step reasoning such as mathematical proving. However, existing approaches often lack an explicit and…

In this paper, we propose a new data synthesis method called \textbf{LogicPro}, which leverages LeetCode-style algorithm \underline{Pro}blems and their corresponding \underline{Pro}gram solutions to synthesize Complex \underline{Logic}al…

Vision-Language Models (VLMs) excel at understanding single images, aided by high-quality instruction datasets. However, multi-image reasoning remains underexplored in the open-source community due to two key challenges: (1) scaling…

Recent works have shown that Large Language Models (LLMs) can facilitate the grounding of instructions for robotic task planning. Despite this progress, most existing works have primarily focused on utilizing raw images to aid LLMs in…

The knowledge-grounded dialogue task aims to generate responses that convey information from given knowledge documents. However, it is a challenge for the current sequence-based model to acquire knowledge from complex documents and…

Synthesizing high-quality training data is crucial for enhancing domain models' reasoning abilities. Existing methods face limitations in long-tail knowledge coverage, effectiveness verification, and interpretability. Knowledge-graph-based…

Despite the strong abilities, large language models (LLMs) still suffer from hallucinations and reliance on outdated knowledge, raising concerns in knowledge-intensive tasks. Graph-based retrieval-augmented generation (GRAG) enriches LLMs…

We propose CoT-Self-Instruct, a synthetic data generation method that instructs LLMs to first reason and plan via Chain-of-Thought (CoT) based on given seed tasks, and then generate a new synthetic example of similar quality and complexity.…

Recent studies have demonstrated the efficacy of using Reinforcement Learning (RL) in building reasoning models that articulate chains of thoughts prior to producing final answers. However, despite ongoing advances that aim at enabling…

Large language models have achieved remarkable progress on complex reasoning tasks. However, they often implicitly fabricate information when inputs are incomplete, producing confident but unreliable conclusions -- a failure mode we term…

In mathematical reasoning tasks, the advancement of Large Language Models (LLMs) relies heavily on high-quality training data with clearly defined and well-graded difficulty levels. However, existing data synthesis methods often suffer from…

Knowledge graphs provide structured and reliable information for many real-world applications, motivating increasing interest in combining large language models (LLMs) with graph-based retrieval to improve factual grounding. Recent…

While Multimodal Large Language Models have achieved human-like performance on many visual and textual reasoning tasks, their proficiency in fine-grained spatial understanding, such as route tracing on maps remains limited. Unlike humans,…

Recently there has been increasing interest in developing and deploying deep graph learning algorithms for many tasks, such as fraud detection and recommender systems. Albeit, there is a limited number of publicly available graph-structured…

Long text generation is an important but challenging task.The main problem lies in learning sentence-level semantic dependencies which traditional generative models often suffer from. To address this problem, we propose a Multi-hop…

In knowledge-intensive tasks, especially in high-stakes domains like medicine and law, it is critical not only to retrieve relevant information but also to provide causal reasoning and explainability. Large language models (LLMs) have…

Large language models (LLMs) often suffer from hallucination, generating factually incorrect statements when handling questions beyond their knowledge and perception. Retrieval-augmented generation (RAG) addresses this by retrieving…

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…

The generation of explanation graphs is a significant task that aims to produce explanation graphs in response to user input, revealing the internal reasoning process. This task is challenging due to the significant discrepancy between…

Multi-hop question answering over knowledge graphs remains computationally challenging due to the combinatorial explosion of possible reasoning paths. Recent approaches rely on expensive Large Language Model (LLM) inference for both entity…