Less but Sufficient: Relation Knowledge Selects Compact Knowledge-Graph Contexts, and What External Checks Can and Cannot Catch
cs.CL
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/meta-llama/llama-models
Terminology
Sources
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
- Premise Order Matters in Reasoning with Large Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Gemma 3 Technical Report
- The Llama 3 Herd of Models
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
- Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
- EXAONE 3.5: Series of Large Language Models for Real-world Use Cases
- Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- Qwen2.5 Technical Report
- Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought
- Large Language Models Can Be Easily Distracted by Irrelevant Context
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
- How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?
- Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
- Qwen3 Technical Report
- Making Retrieval-Augmented Language Models Robust to Irrelevant Context
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data