paper-with-me

홈 › Papers

KGLens: Towards Efficient and Effective Knowledge Probing of Large Language Models with Knowledge Graphs

2023-12-15 · Shangshang Zheng, He Bai, Yizhe Zhang, Yi Su, Xiaochuan Niu, Navdeep Jaitly

Large Language Models (LLMs) might hallucinate facts, while curated Knowledge Graph (KGs) are typically factually reliable especially with domain-specific knowledge. Measuring the alignment between KGs and LLMs can effectively probe the factualness and identify the knowledge blind spots of LLMs. However, verifying the LLMs over extensive KGs can be expensive. In this paper, we present KGLens, a Thompson-sampling-inspired framework aimed at effectively and efficiently measuring the alignment between KGs and LLMs. KGLens features a graph-guided question generator for converting KGs into natural language, along with a carefully designed importance sampling strategy based on parameterized KG structure to expedite KG traversal. Our simulation experiment compares the brute force method with KGLens under six different sampling methods, demonstrating that our approach achieves superior probing efficiency. Leveraging KGLens, we conducted in-depth analyses of the factual accuracy of ten LLMs across three large domain-specific KGs from Wikidata, composing over 19K edges, 700 relations, and 21K entities. Human evaluation results indicate that KGLens can assess LLMs with a level of accuracy nearly equivalent to that of human annotators, achieving 95.7% of the accuracy rate.

📄 PDF Abstract BibTeX arXiv:2312.11539

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graphs

Methods 이 논문이 사용한 방법론

Focus 설명 없음
AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models

2024-06-18 · Xin Zhao, Naoki Yoshinaga, Daisuke Oba

Language models often struggle with handling factual knowledge, exhibiting factual hallucination issue. This makes it vital to evaluate the models' ability to recall its parametric knowledge about facts. In this study, w…

DecoderHallucinationIn-Context LearningKnowledge Probing

Knowledge Trees: Gradient Boosting Decision Trees on Knowledge Neurons as Probing Classifier

2023-12-17 · Sergey A. Saltykov

To understand how well a large language model captures certain semantic or syntactic features, researchers typically apply probing classifiers. However, the accuracy of these classifiers is critical for the correct inter…

Language ModelingLanguage ModellingLarge Language Modelregression+1

An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models

2021-09-06 · Tianxing He, Kyunghyun Cho, James Glass

Prompt-based knowledge probing for 1-hop relations has been used to measure how much world knowledge is stored in pretrained language models. Existing work uses considerable amounts of data to tune the prompts for better…

Knowledge ProbingPrompt EngineeringWorld Knowledge

Probing Language Models on Their Knowledge Source

2024-10-08 · Zineddine Tighidet, Andrea Mogini, Jiali Mei, Benjamin Piwowarski 외

Large Language Models (LLMs) often encounter conflicts between their learned, internal (parametric knowledge, PK) and external knowledge provided during inference (contextual knowledge, CK). Understanding how LLMs models…

Probing Language Models

UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models

2025-12-19 · Jiajun Wu, Jian Yang, Wei Zhang, Lin Jing 외 arxiv

Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, their effectiveness heavily relies on supervised training with extensive labeled (e.g., question-answering pairs) …

Code Generation