Faithful Knowledge Graph Explanations for Commonsense Reasoning
- URL: http://arxiv.org/abs/2310.04910v4
- Date: Sat, 22 Jun 2024 16:03:52 GMT
- Title: Faithful Knowledge Graph Explanations for Commonsense Reasoning
- Authors: Weihe Zhai, Arkaitz Zubiaga,
- Abstract summary: Fusion of language models (LMs) and knowledge graphs (KGs) is widely used in commonsense question answering.
Current methods often overlook path decoding faithfulness, leading to divergence between graph encoder outputs and model predictions.
We identify confounding effects and LM-KG misalignment as key factors causing spurious explanations.
- Score: 7.242609314791262
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: The fusion of language models (LMs) and knowledge graphs (KGs) is widely used in commonsense question answering, but generating faithful explanations remains challenging. Current methods often overlook path decoding faithfulness, leading to divergence between graph encoder outputs and model predictions. We identify confounding effects and LM-KG misalignment as key factors causing spurious explanations. To address this, we introduce the LM-KG Fidelity metric to assess KG representation reliability and propose the LM-KG Distribution-aware Alignment (\textit{LKDA}) algorithm to improve explanation faithfulness. Without ground truth, we evaluate KG explanations using the proposed Fidelity-Sparsity Trade-off Curve. Experiments on CommonsenseQA and OpenBookQA show that LKDA significantly enhances explanation fidelity and model performance, highlighting the need to address distributional misalignment for reliable commonsense reasoning.
Related papers
- FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering [46.41364317172677]
We propose a retrieval-exploration interactive method, FiDelis, to handle intermediate steps of reasoning grounded by external knowledge graphs.
We incorporate the logic and common-sense reasoning of LLMs into the knowledge retrieval process, which provides more accurate recalling performance.
arXiv Detail & Related papers (2024-05-22T17:56:53Z) - Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering [90.30473970040362]
We propose a training-free method called Generate-on-Graph (GoG) that can generate new factual triples while exploring on Knowledge Graphs (KGs)
Specifically, we propose a selecting-generating-answering framework, which not only treat the LLM as an agent to explore on KGs, but also treat it as a KG to generate new facts based on the explored subgraph.
arXiv Detail & Related papers (2024-04-23T04:47:22Z) - Faithful Path Language Modeling for Explainable Recommendation over Knowledge Graph [15.40937702266105]
We introduce PEARLM (Path-based Explainable-Accurate Recommender based on Language Modelling), which innovates with a Knowledge Graph Constraint Decoding (KGCD) mechanism.
This mechanism ensures zero incidence of corrupted paths by enforcing adherence to valid KG connections at the decoding level.
We validate the effectiveness of our approach through a rigorous empirical assessment, employing a newly proposed metric that quantifies the integrity of explanation paths.
arXiv Detail & Related papers (2023-10-25T08:14:49Z) - Reasoning on Graphs: Faithful and Interpretable Large Language Model
Reasoning [104.92384929827776]
Large language models (LLMs) have demonstrated impressive reasoning abilities in complex tasks.
They lack up-to-date knowledge and experience hallucinations during reasoning.
Knowledge graphs (KGs) offer a reliable source of knowledge for reasoning.
arXiv Detail & Related papers (2023-10-02T10:14:43Z) - Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph
Completion [69.55700751102376]
Few-shot knowledge graph completion (FKGC) aims to predict missing facts for unseen relations with few-shot associated facts.
Existing FKGC methods are based on metric learning or meta-learning, which often suffer from the out-of-distribution and overfitting problems.
In this paper, we propose a normalizing flow-based neural process for few-shot knowledge graph completion (NP-FKGC)
arXiv Detail & Related papers (2023-04-17T11:42:28Z) - Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction [0.0]
We propose a novel model entitled DEKG-ILP (Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction)
The module CLRM is developed to extract global relation-based semantic features that are shared between original KGs and DEKGs.
The module GSM is proposed to extract the local subgraph topological information around each link in KGs.
arXiv Detail & Related papers (2022-09-03T10:58:24Z) - Explainable Sparse Knowledge Graph Completion via High-order Graph
Reasoning Network [111.67744771462873]
This paper proposes a novel explainable model for sparse Knowledge Graphs (KGs)
It combines high-order reasoning into a graph convolutional network, namely HoGRN.
It can not only improve the generalization ability to mitigate the information insufficiency issue but also provide interpretability.
arXiv Detail & Related papers (2022-07-14T10:16:56Z) - DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation
with Relational GNN [59.160401038969795]
We propose differentiable sampling on Knowledge Graph for Recommendation with GNN (DSKReG)
We devise a differentiable sampling strategy, which enables the selection of relevant items to be jointly optimized with the model training procedure.
The experimental results demonstrate that our model outperforms state-of-the-art KG-based recommender systems.
arXiv Detail & Related papers (2021-08-26T16:19:59Z) - QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question
Answering [122.84513233992422]
We propose a new model, QA-GNN, which addresses the problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs)
We show its improvement over existing LM and LM+KG models, as well as its capability to perform interpretable and structured reasoning.
arXiv Detail & Related papers (2021-04-13T17:32:51Z)
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.