Lost-in-Distance: Impact of Contextual Proximity on LLM Performance in Graph Tasks

• URL: http://arxiv.org/abs/2410.01985v2
• Date: Thu, 02 Jan 2025 04:15:37 GMT
• Title: Lost-in-Distance: Impact of Contextual Proximity on LLM Performance in Graph Tasks
• Abstract summary: We show that Large Language Models exhibit blind spots that impair their ability to retrieve and process relevant contextual data effectively.<n>We propose a formulation for the lost-in-distance phenomenon and demonstrate that lost-in-distance and lost-in-the middle phenomenas occur independently.
• Score: 10.899834454573215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite significant advancements, Large Language Models (LLMs) exhibit blind spots that impair their ability to retrieve and process relevant contextual data effectively. We demonstrate that LLM performance in graph tasks with complexities beyond the "needle-in-a-haystack" scenario-where solving the problem requires cross-referencing and reasoning across multiple subproblems jointly-is influenced by the proximity of relevant information within the context, a phenomenon we term "lost-in-distance". We examine two fundamental graph tasks: identifying common connections between two nodes and assessing similarity among three nodes, and show that the model's performance in these tasks significantly depends on the relative positioning of common edges. We evaluate three publicly available LLMs using various graph encoding techniques that represent graph structures for LLM input. We propose a formulation for the lost-in-distance phenomenon and demonstrate that lost-in-distance and lost-in-the middle phenomenas occur independently. Results indicate that model accuracy can decline by up to 6x as the distance between node connections increases, independent of graph encoding and model size.

Related papers

• POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment [0.7081442513665945]
  Point-of-interest (POI) recommendation models based on graph neural networks achieve strong performance by propagating collaborative signals over user-item interactions.<n>We propose Multi-Graph Contrastive Learning (LLM-MGCL), a multi-graph neural network that uses semantic and spatial information about items to extend the LightGCN backbone.<n>Our results suggest that externally grounded, LLM-derived item knowledge can effectively compensate for missing collaborative signal and mitigate the item cold-start problem in POI recommendation.
  arXiv  Detail & Related papers  (2026-08-17T11:01:12Z)
• OWLEYE: Zero-Shot Learner for Cross-Domain Graph Data Anomaly Detection [48.77471686671269]
  OWLEYE is a novel framework that learns transferable patterns of normal behavior from multiple graphs.<n>We show that OWLEYE achieves superior performance and generalizability compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-01-27T02:08:18Z)
• Towards Efficient LLM-aware Heterogeneous Graph Learning [47.42705995672551]
  We propose an Efficient LLM-Aware framework for heterogeneous graphs.<n>Our proposed ELLA outperforms state-of-the-art methods in the performance and efficiency.
  arXiv  Detail & Related papers  (2025-11-22T05:38:03Z)
• Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference [7.817259532290553]
  Large language models (LLMs) are increasingly used for text-rich graph machine learning tasks.<n>Despite a surge of interest, the field lacks a principled understanding of the capabilities of LLMs in their interaction with graph data.
  arXiv  Detail & Related papers  (2025-09-23T00:46:21Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation [75.9865035064794]
  Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information.<n>Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system.<n>We propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase.
  arXiv  Detail & Related papers  (2025-05-22T05:15:27Z)
• Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data [10.907949155931474]
  We study how large language models (LLMs) process graph-structured data.<n>We uncover unique phenomena regarding how LLMs apply attention to graph-structured data.<n>We analyze these findings to improve the modeling of such data by LLMs.
  arXiv  Detail & Related papers  (2025-05-04T14:40:31Z)
• Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition [3.330229314824913]
  Self-supervised learning (SSL) in graphs has garnered significant attention, particularly in employing Graph Neural Networks (GNNs) with pretext tasks. We show that existing methods position opposite ends of a spectrum driven by the graph embedding smoothness, with each end corresponding to outperformance on specific downstream tasks. A framework, BSG, introduces novel loss functions designed to supplement the representation quality in graph-based SSL.
  arXiv  Detail & Related papers  (2025-04-16T12:09:56Z)
• Path-of-Thoughts: Extracting and Following Paths for Robust Relational Reasoning with Large Language Models [62.12031550252253]
  We present Path-of-Thoughts (PoT), a novel framework designed to tackle relation reasoning. PoT efficiently extracts a task-agnostic graph that identifies crucial entities, relations, and attributes within the problem context. PoT identifies relevant reasoning chains within the graph corresponding to the posed question, facilitating inference of potential answers.
  arXiv  Detail & Related papers  (2024-12-23T20:27:12Z)
• Revisiting the Graph Reasoning Ability of Large Language Models: Case Studies in Translation, Connectivity and Shortest Path [53.71787069694794]
  We focus on the graph reasoning ability of Large Language Models (LLMs) We revisit the ability of LLMs on three fundamental graph tasks: graph description translation, graph connectivity, and the shortest-path problem. Our findings suggest that LLMs can fail to understand graph structures through text descriptions and exhibit varying performance for all these fundamental tasks.
  arXiv  Detail & Related papers  (2024-08-18T16:26:39Z)
• Can Graph Learning Improve Planning in LLM-based Agents? [61.47027387839096]
  Task planning in language agents is emerging as an important research topic alongside the development of large language models (LLMs) In this paper, we explore graph learning-based methods for task planning, a direction that is to the prevalent focus on prompt design. Our interest in graph learning stems from a theoretical discovery: the biases of attention and auto-regressive loss impede LLMs' ability to effectively navigate decision-making on graphs.
  arXiv  Detail & Related papers  (2024-05-29T14:26:24Z)
• Talk like a Graph: Encoding Graphs for Large Language Models [15.652881653332194]
  We study the first comprehensive study of encoding graph-structured data as text for consumption by large language models (LLMs) We show that LLM performance on graph reasoning tasks varies on three fundamental levels: (1) the graph encoding method, (2) the nature of the graph task itself, and (3) interestingly, the very structure of the graph considered.
  arXiv  Detail & Related papers  (2023-10-06T19:55:21Z)
• Spatio-temporal MLP-graph network for 3D human pose estimation [8.267311047244881]
  Graph convolutional networks and their variants have shown significant promise in 3D human pose estimation. We introduce a new weighted Jacobi feature rule obtained through graph filtering with implicit propagation fairing. We also employ adjacency modulation with the aim of learning meaningful correlations beyond defined between body joints.
  arXiv  Detail & Related papers  (2023-08-29T14:00:55Z)
• Multi-Grained Multimodal Interaction Network for Entity Linking [65.30260033700338]
  Multimodal entity linking task aims at resolving ambiguous mentions to a multimodal knowledge graph. We propose a novel Multi-GraIned Multimodal InteraCtion Network $textbf(MIMIC)$ framework for solving the MEL task.
  arXiv  Detail & Related papers  (2023-07-19T02:11:19Z)
• Learning Strong Graph Neural Networks with Weak Information [64.64996100343602]
  We develop a principled approach to the problem of graph learning with weak information (GLWI) We propose D$2$PT, a dual-channel GNN framework that performs long-range information propagation on the input graph with incomplete structure, but also on a global graph that encodes global semantic similarities.
  arXiv  Detail & Related papers  (2023-05-29T04:51:09Z)
• Localized Contrastive Learning on Graphs [110.54606263711385]
  We introduce a simple yet effective contrastive model named Localized Graph Contrastive Learning (Local-GCL) In spite of its simplicity, Local-GCL achieves quite competitive performance in self-supervised node representation learning tasks on graphs with various scales and properties.
  arXiv  Detail & Related papers  (2022-12-08T23:36:00Z)
• Simultaneous Multiple Object Detection and Pose Estimation using 3D Model Infusion with Monocular Vision [21.710141497071373]
  Multiple object detection and pose estimation are vital computer vision tasks. We propose simultaneous neural modeling of both using monocular vision and 3D model infusion. Our Simultaneous Multiple Object detection and Pose Estimation network (SMOPE-Net) is an end-to-end trainable multitasking network.
  arXiv  Detail & Related papers  (2022-11-21T05:18:56Z)
• Learning-based Point Cloud Registration for 6D Object Pose Estimation in the Real World [55.7340077183072]
  We tackle the task of estimating the 6D pose of an object from point cloud data. Recent learning-based approaches to addressing this task have shown great success on synthetic datasets. We analyze the causes of these failures, which we trace back to the difference between the feature distributions of the source and target point clouds.
  arXiv  Detail & Related papers  (2022-03-29T07:55:04Z)
• Distributed Multi-Agent Reinforcement Learning Based on Graph-Induced Local Value Functions [7.6860514640178]
  We propose a general computationally efficient distributed framework for cooperative multi-agent reinforcement learning (MARL) We introduce three coupling graphs describing three types of inter-agent couplings in MARL. We propose two distributed RL approaches based on local value-functions derived from the coupling graphs.
  arXiv  Detail & Related papers  (2022-02-26T03:01:51Z)
• DRG: Dual Relation Graph for Human-Object Interaction Detection [65.50707710054141]
  We tackle the challenging problem of human-object interaction (HOI) detection. Existing methods either recognize the interaction of each human-object pair in isolation or perform joint inference based on complex appearance-based features. In this paper, we leverage an abstract spatial-semantic representation to describe each human-object pair and aggregate the contextual information of the scene via a dual relation graph.
  arXiv  Detail & Related papers  (2020-08-26T17:59:40Z)
• Taskology: Utilizing Task Relations at Scale [28.09712466727001]
  We show that we can leverage the inherent relationships among collections of tasks, as they are trained jointly. explicitly utilizing the relationships between tasks allows improving their performance while dramatically reducing the need for labeled data. We demonstrate our framework on subsets of the following collection of tasks: depth and normal prediction, semantic segmentation, 3D motion and ego-motion estimation, and object tracking and 3D detection in point clouds.
  arXiv  Detail & Related papers  (2020-05-14T22:53:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.