Write Facts the Way Models Read Them: Lifting the Two-Hop Curse
cs.CL, cs.LG
Submitted: 2026-11-01
Updated: 2026-11-14
Comments: 17 pages, 4 figures, 16 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Lessons from Studying Two-Hop Latent Reasoning
- The Llama 3 Herd of Models
- PropMEND: Hypernetworks for Knowledge Propagation in LLMs
- Qwen2.5 Technical Report
- Qwen3 Technical Report
- ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall
- Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models
- Addressing the Reasoning Gap: Mechanistic Circuit-Based Knowledge Editing in Large Language Models
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