Papers with knowledge representations

14 papers
BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have revolutionized various domains with their remarkable capabilities, but their massive parameter sizes pose significant challenges for fine-tuning and inference.
Approach: They propose a Bayesian Knowledge Distillation framework for compact Large Language Models in resource-constrained fine-tuning scenarios that employs Logits Dual-Scaling, Knowledge Alignment Module, and Bayes Distillations Optimization.
Outcome: The proposed framework outperforms baseline methods on various state-of-the-art LLMs, including LLaMA, Qwen2, Bloom, and Vicuna.
Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text (D19-60)

Copied to clipboard

Challenge: Existing work on modeling semantic plausibility has focused on physical plausability but distributional methods fail when tested in supervised settings.
Approach: They propose to use large pretrained language models to model plausibility in supervised settings by extracting attested events from a large corpus and injecting explicit commonsense knowledge into a distributional model.
Outcome: The proposed model is effective in modeling plausibility in a supervised setting.
CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge (2022.acl-demo)

Copied to clipboard

Challenge: Existing methods focus on entity-centric knowledge, but CogKGE supports heterogeneous knowledge.
Approach: They propose a knowledge graph embedding toolkit to represent multi-source and heterogeneous knowledge.
Outcome: The proposed toolkit provides a unified programming framework for KGE tasks and a series of knowledge representations for downstream tasks.
In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering (2021.acl-short)

Copied to clipboard

Challenge: Current Visual Question Answering (VQA) models are trained on labelled data that may be insufficient to learn complex knowledge representations.
Approach: They propose a method to integrate external knowledge into a visual pre-trained model by integrating facts extracted from a knowledge base.
Outcome: The proposed method outperforms baseline models on the KVQA dataset benchmark by 19% and shows that it is weaker than previous models.
EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to modifying large language models require continual updates to rectify outdated or erroneous knowledge.
Approach: They propose a model editing strategy that mitigates catastrophic interference through sequential null-space alignment.
Outcome: EvoEdit achieves better or comparable performance than prior state-of-the-art techniques with up to 3.53 speedup.
Relational World Knowledge Representation in Contextual Language Models: A Review (2021.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge bases are organized according to manual schemas that limit their expressiveness and require significant human engineering and maintenance.
Approach: They propose to organize knowledge representation strategies in LMs by the level of KB supervision provided . they propose to highlight notable models, evaluation tasks, and findings .
Outcome: The proposed model can internalize and express relational knowledge in more flexible forms.
Past, Present, and Future: Conversational Emotion Recognition through Structural Modeling of Psychological Knowledge (2021.findings-emnlp)

Copied to clipboard

Challenge: Conversational Emotion Recognition (CER) is a task to predict the emotion of an utterance in the context of a conversation.
Approach: They propose a pSychological-Knowledge-Aware Interaction Graph to model the emotional state of an utterance in the context of a conversation.
Outcome: The proposed method achieves state-of-the-art and competitive performance on four popular CER datasets.
Bring Invariant to Variant: A Contrastive Prompt-based Framework for Temporal Knowledge Graph Forecasting (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for temporal knowledge graph forecasting are insufficient structural contexts to learn effective representations.
Approach: They propose a Contrastive Prompt-based framework with Entity background information for TKG forecasting that brings time-invariant entity background information to time-variant structural information.
Outcome: The proposed framework is effective and stays competitive in inference with limited structural information.
Knowledge Graph Embedding with Hierarchical Relation Structure (D18-1)

Copied to clipboard

Challenge: Existing knowledge graph embedding models embed entities and relations into latent vectors without leveraging rich information from relation structure.
Approach: They extend existing KGE models to learn knowledge representations by leveraging relation structure . authors say their approach is capable of extending other KGEs .
Outcome: The proposed approach can extend existing KGE models, and validates against baselines.
Knowledge Association with Hyperbolic Knowledge Graph Embeddings (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for knowledge graphs (KGs) depend on high embedding dimensions and hierarchical structures to achieve expressiveness.
Approach: They propose a hyperbolic relational graph neural network for KG embedding and capture knowledge associations with a high-dimensional transformation.
Outcome: Experiments on entity alignment and type inference show the proposed method is effective and efficient.
Context or Knowledge is Not Always Necessary: A Contrastive Learning Framework for Emotion Recognition in Conversations (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on modeling context-sensitive dependencies and knowledge-sensitive dependences.
Approach: They propose a framework based on contrastive learning called CKCL to distinguish utterances for better vector representations.
Outcome: The proposed framework outperforms state-of-the-art models on four datasets.
Differentiated Vision: Unveiling Entity-Specific Visual Modality Requirements for Multimodal Knowledge Graph (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to extract features from images of entities overlook varying relevance of visual information across entities.
Approach: a new model integrates structural and multimodal information of entities into a multimodal knowledge graph . a model evaluates the necessity of visual modality for each entity based on its attributes .
Outcome: The proposed model improves on existing methods by adjusting visual data to different entity types.
MicroEdit: Neuron-level Knowledge Disentanglement and Localization in Lifelong Model Editing (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for enhancing large language models are designed for single or limited edits, lacking the capacity to support long-term, multi-round knowledge updates.
Approach: They propose a neuron-level editing method that performs minimal interventions within large language models (LLMs) by leveraging a sparse autoencoder, MicroEdit disentangles knowledge representations and activates only a minimal set of necessary neurons for precise parameter updates.
Outcome: Extensive experiments show that MicroEdit outperforms prior methods and robustly handles lifelong knowledge editing across QA and Hallucination settings on LLaM and Mistral.
Knowledge Vector of Logical Reasoning in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Logical reasoning is a central capability in LLMs, but understanding their abilities remains poorly understood.
Approach: They propose to refine the knowledge representations of each reasoning type in LLMs to encourage complementarity . they propose to use complementary loss and subspace constraint loss to enhance complementarities .
Outcome: The proposed framework encourages complementarity between the different types of reasoning in LLMs.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations