GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics

• URL: http://arxiv.org/abs/2604.02830v1
• Date: Fri, 03 Apr 2026 07:52:26 GMT
• Title: GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics
• Abstract summary: We present GRADE (Gradient Dynamics for knowledge gap detection), which quantifies the knowledge gap via the cross-layer rank ratio of the gradient to that of the corresponding hidden state subspace.<n>We validate modelname on six benchmarks, demonstrating its effectiveness and robustness to input perturbations.<n>In addition, we present a case study showing how the gradient chain can generate interpretable explanations of knowledge gaps for long-form answers.
• Score: 51.647572539626715
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Detecting whether a model's internal knowledge is sufficient to correctly answer a given question is a fundamental challenge in deploying responsible LLMs. In addition to verbalising the confidence by LLM self-report, more recent methods explore the model internals, such as the hidden states of the response tokens to capture how much knowledge is activated. We argue that such activated knowledge may not align with what the query requires, e.g., capturing the stylistic and length-related features that are uninformative for answering the query. To fill the gap, we propose GRADE (Gradient Dynamics for knowledge gap detection), which quantifies the knowledge gap via the cross-layer rank ratio of the gradient to that of the corresponding hidden state subspace. This is motivated by the property of gradients as estimators of the required knowledge updates for a given target. We validate \modelname{} on six benchmarks, demonstrating its effectiveness and robustness to input perturbations. In addition, we present a case study showing how the gradient chain can generate interpretable explanations of knowledge gaps for long-form answers.

Related papers

• Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction [29.717986496967978]
  We propose an interactive agentic framework to systematically extract and quantify the knowledge of Large Language Models.<n>Our method includes four adaptive exploration policies to probe knowledge at different granularities.<n>We observe a clear knowledge scaling law, where larger models consistently extract more knowledge.
  arXiv  Detail & Related papers  (2026-02-01T01:43:44Z)
• Knowledge Boundary Discovery for Large Language Models [1.9967734396620447]
  We propose a reinforcement learning based framework to explore the knowledge boundaries of Large Language Models (LLMs)<n>We define the knowledge boundary by automatically generating two types of questions: (i) those the LLM can confidently answer (within-knowledge boundary) and (ii) those it cannot (beyond-knowledge boundary)<n>We demonstrate that the KBD detects knowledge boundaries of LLMs by automatically finding a set of non-trivial answerable and unanswerable questions.
  arXiv  Detail & Related papers  (2026-01-14T02:19:13Z)
• Knowledge Homophily in Large Language Models [75.12297135039776]
  We investigate an analogous knowledge homophily pattern in Large Language Models (LLMs)<n>We map LLM knowledge into a graph representation through knowledge checking at both the triplet and entity levels.<n>Motivated by this homophily principle, we propose a Graph Neural Network (GNN) regression model to estimate entity-level knowledgeability scores for triplets.
  arXiv  Detail & Related papers  (2025-09-28T09:40:27Z)
• Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities [43.88784275673178]
  Retrieval-Augmented Generation (RAG) shows impressive performance by supplementing and substituting parametric knowledge in Large Language Models (LLMs)<n>We show how triplets located in the gold reasoning path and their variants are used to construct partially relevant knowledge by removing the path that contains the answer.<n>Our awakening-based approach demonstrates greater efficacy in practical applications, outperforms traditional methods that rely on embedding-based similarity.
  arXiv  Detail & Related papers  (2025-08-02T09:54:46Z)
• PropMEND: Hypernetworks for Knowledge Propagation in LLMs [82.99849359892112]
  We present a hypernetwork-based approach for knowledge propagation, named PropMEND.<n>We show almost 2x accuracy on challenging multi-hop questions whose answers are not explicitly stated in the injected fact.<n>We also introduce a new dataset, Controlled RippleEdit, to evaluate the generalization of our hypernetwork.
  arXiv  Detail & Related papers  (2025-06-10T15:44:19Z)
• Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation [77.10390725623125]
  retrieval-augmented generation (RAG) is widely employed to expand their knowledge scope.<n>Since RAG has shown promise in knowledge-intensive tasks like open-domain question answering, its broader application to complex tasks and intelligent assistants has further advanced its utility.<n>We present a systematic investigation of the intrinsic mechanisms by which RAGs integrate internal (parametric) and external (retrieved) knowledge.
  arXiv  Detail & Related papers  (2025-05-17T13:13:13Z)
• Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference [82.557441484339]
  We propose a method to detect the knowledge boundary of Vision Large Language Models (VLLMs)<n> Experimental results on various types of Visual Question Answering datasets show that our method successfully depicts a VLLM's knowledge boundary.
  arXiv  Detail & Related papers  (2025-02-25T09:32:08Z)
• IAO Prompting: Making Knowledge Flow Explicit in LLMs through Structured Reasoning Templates [7.839338724237275]
  We introduce IAO (Input-Action-Output), a structured template-based method that explicitly models how Large Language Models access and apply their knowledge.<n>IAO decomposes problems into sequential steps, each clearly identifying the input knowledge being used, the action being performed, and the resulting output.<n>Our findings provide insights into both knowledge representation within LLMs and methods for more reliable knowledge application.
  arXiv  Detail & Related papers  (2025-02-05T11:14:20Z)
• KaLM: Knowledge-aligned Autoregressive Language Modeling via Dual-view Knowledge Graph Contrastive Learning [74.21524111840652]
  This paper proposes textbfKaLM, a textitKnowledge-aligned Language Modeling approach.<n>It fine-tunes autoregressive large language models to align with KG knowledge via the joint objective of explicit knowledge alignment and implicit knowledge alignment.<n> Notably, our method achieves a significant performance boost in evaluations of knowledge-driven tasks.
  arXiv  Detail & Related papers  (2024-12-06T11:08:24Z)
• Fine-grained Stateful Knowledge Exploration: Effective and Efficient Graph Retrieval with Large Language Models [19.049828741139425]
  Large Language Models (LLMs) have shown impressive capabilities, yet updating their knowledge remains a significant challenge.<n>Most existing methods use a paradigm that treats the whole question as the objective, with relevant knowledge being incrementally retrieved from the knowledge graph.<n>We propose FiSKE, a novel paradigm for Fine-grained Stateful Knowledge Exploration.
  arXiv  Detail & Related papers  (2024-01-24T13:36:50Z)
• R-Tuning: Instructing Large Language Models to Say `I Don't Know' [66.11375475253007]
  Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. Previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. We present a new approach called Refusal-Aware Instruction Tuning (R-Tuning) Experimental results demonstrate R-Tuning effectively improves a model's ability to answer known questions and refrain from answering unknown questions.
  arXiv  Detail & Related papers  (2023-11-16T08:45:44Z)
• Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation [109.8527403904657]
  We show that large language models (LLMs) possess unwavering confidence in their knowledge and cannot handle the conflict between internal and external knowledge well. Retrieval augmentation proves to be an effective approach in enhancing LLMs' awareness of knowledge boundaries. We propose a simple method to dynamically utilize supporting documents with our judgement strategy.
  arXiv  Detail & Related papers  (2023-07-20T16:46:10Z)

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.