Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement

arXiv:2511.01706 · cs.CL, cs.AI, cs.LG · Submitted 2025-11-03 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2025-11-03

Updated: 2026-09-01

Code: https://github.com/copenlu/pk-ck-knowledge-disentanglement

Terminology

• Alignment — 17× in this paper · explained in 1 episode
• Activation Patching — 9× in this paper · explained in 2 episodes
• Hallucination — 9× in this paper · explained in 3 episodes
• Parametric Knowledge — 9× in this paper
• Grounding — 8× in this paper · explained in 3 episodes
• Natural Language Explanation — 7× in this paper
• Context Knowledge — 6× in this paper
• Empirical Methods in Natural Language Processing — 6× in this paper
• Large Language Models (LLMs) — 4× in this paper · explained in 6 episodes
• Question Answering — 4× in this paper
• Robustness — 4× in this paper · explained in 5 episodes
• Kernel Density Estimate — 3× in this paper
• RAG — 3× in this paper · explained in 3 episodes
• Chain-of-Thought (CoT) — 2× in this paper · explained in 4 episodes
• Chain-of-Thought (CoT) Prompting — 2× in this paper · explained in 3 episodes
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Claim Verification — 2× in this paper
• Interpretability — 2× in this paper · explained in 15 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Contextual Understanding — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Singular Value Decomposition (SVD) — 1× in this paper · explained in 2 episodes
• Systematic Bias — 1× in this paper · explained in 3 episodes

Sources

• Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models
• Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models
• The Llama 3 Herd of Models
• Mistral 7B
• "Lost-in-the-Later": Framework for Quantifying Contextual Grounding in Large Language Models
• Evaluating the External and Parametric Knowledge Fusion of Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering