# Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension

arXiv: https://arxiv.org/abs/2501.01332 · HTML: https://mlsanity.com/paper/2501.01332/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 2 Jan 2025.

## Builds on (most cited first, 20 of 20)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [Physics of Language Models: Part 3.1, Knowledge Storage and Extraction](https://mlsanity.com/paper/2309.14316/) (2023)
- [Do Large Language Models Know What They Don't Know?](https://mlsanity.com/paper/2305.18153/) (2023)
- [Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?](https://mlsanity.com/paper/2405.05904/) (2024)
- [Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?](https://mlsanity.com/paper/2308.10168/) (2023)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM](https://mlsanity.com/paper/2408.12076/) (2024)
- [Large language models surpass human experts in predicting neuroscience results](https://mlsanity.com/paper/2403.03230/) (2024)
- [Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection](https://mlsanity.com/paper/2403.09972/) (2024)
- [KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking](https://mlsanity.com/paper/2404.02935/) (2024)
- [Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods](https://mlsanity.com/paper/2404.18655/) (2024)
- [KGLens: Towards Efficient and Effective Knowledge Probing of Large Language Models with Knowledge Graphs](https://mlsanity.com/paper/2312.11539/) (2023)

## Abstract (arXiv)

Understanding how large language models (LLMs) acquire, retain, and apply knowledge remains an open challenge. This paper introduces a novel framework, K-(CSA)^2, which categorizes LLM knowledge along two dimensions: correctness and confidence. The framework defines six categories of knowledge, ranging from highly confident correctness to confidently held misconceptions, enabling a nuanced evaluation of model comprehension beyond binary accuracy. Using this framework, we demonstrate how techniques like chain-of-thought prompting and reinforcement learning with human feedback fundamentally alter the knowledge structures of internal (pre-trained) and external (context-dependent) knowledge in LLMs. CoT particularly enhances base model performance and shows synergistic benefits when applied to aligned LLMs. Moreover, our layer-wise analysis reveals that higher layers in LLMs encode more high-confidence knowledge, while low-confidence knowledge tends to emerge in middle-to-lower layers.