# Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods

arXiv: https://arxiv.org/abs/2404.18655 · HTML: https://mlsanity.com/paper/2404.18655/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 21 of 21)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models](https://mlsanity.com/paper/2301.04213/) (2023)
- [Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions](https://mlsanity.com/paper/2005.06676/) (2020)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting](https://mlsanity.com/paper/2212.09535/) (2022)
- [Neuron-level Interpretation of Deep NLP Models: A Survey](https://mlsanity.com/paper/2108.13138/) (2021)
- [Input Similarity from the Neural Network Perspective](https://mlsanity.com/paper/2102.05262/) (2021)
- [Combining Feature and Instance Attribution to Detect Artifacts](https://mlsanity.com/paper/2107.00323/) (2021)
- [An Empirical Comparison of Instance Attribution Methods for NLP](https://mlsanity.com/paper/2104.04128/) (2021)
- [Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets](https://mlsanity.com/paper/2302.13959/) (2023)

## Built on by (most cited first, 9 of 9)

- [DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2407.17023/) (2024)
- [Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework](https://mlsanity.com/paper/2406.15085/) (2024)
- [Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation](https://mlsanity.com/paper/2504.14856/) (2025)
- [Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality](https://mlsanity.com/paper/2509.23765/) (2025)
- [Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms](https://mlsanity.com/paper/2601.20131/) (2026)
- [Guiding LLMs to Generate High-Fidelity and High-Quality Counterfactual Explanations for Text Classification](https://mlsanity.com/paper/2503.04463/) (2025)
- [Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement](https://mlsanity.com/paper/2511.01706/) (2025)
- [Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025](https://mlsanity.com/paper/2603.09654/) (2026)
- [Decoding Knowledge in Large Language Models: A Framework for Categorization and Comprehension](https://mlsanity.com/paper/2501.01332/) (2025)

## Abstract (arXiv)

Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant challenges for understanding a model's inner workings and further for updating or correcting this embedded knowledge without the significant cost of retraining. This underscores the importance of unveiling exactly what knowledge is stored and its association with specific model components. Instance Attribution (IA) and Neuron Attribution (NA) offer insights into this training-acquired knowledge, though they have not been compared systematically. Our study introduces a novel evaluation framework to quantify and compare the knowledge revealed by IA and NA. To align the results of the methods we introduce the attribution method NA-Instances to apply NA for retrieving influential training instances, and IA-Neurons to discover important neurons of influential instances discovered by IA. We further propose a comprehensive list of faithfulness tests to evaluate the comprehensiveness and sufficiency of the explanations provided by both methods. Through extensive experiments and analysis, we demonstrate that NA generally reveals more diverse and comprehensive information regarding the LM's parametric knowledge compared to IA. Nevertheless, IA provides unique and valuable insights into the LM's parametric knowledge, which are not revealed by NA. Our findings further suggest the potential of a synergistic approach of combining the diverse findings of IA and NA for a more holistic understanding of an LM's parametric knowledge.