# Characterizing Mechanisms for Factual Recall in Language Models

arXiv: https://arxiv.org/abs/2310.15910 · HTML: https://mlsanity.com/paper/2310.15910/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Impact of Pretraining Term Frequencies on Few-Shot Reasoning](https://mlsanity.com/paper/2202.07206/) (2022)
- [Counterfactual Story Reasoning and Generation](https://mlsanity.com/paper/1909.04076/) (2019)
- [Understanding Transformer Memorization Recall Through Idioms](https://mlsanity.com/paper/2210.03588/) (2022)
- [Counterfactual reasoning: Testing language models' understanding of hypothetical scenarios](https://mlsanity.com/paper/2305.16572/) (2023)

## Built on by (most cited first, 30 of 48)

- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [LoFiT: Localized Fine-tuning on LLM Representations](https://mlsanity.com/paper/2406.01563/) (2024)
- [When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models](https://mlsanity.com/paper/2508.02087/) (2025)
- [Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding](https://mlsanity.com/paper/2502.01563/) (2025)
- [Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions](https://mlsanity.com/paper/2407.15018/) (2024)
- [Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization](https://mlsanity.com/paper/2410.12949/) (2024)
- [Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective](https://mlsanity.com/paper/2505.12886/) (2025)
- [Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models](https://mlsanity.com/paper/2403.19521/) (2024)
- [UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation](https://mlsanity.com/paper/2405.20612/) (2024)
- [Taming Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2503.10996/) (2025)
- [Undesirable Memorization in Large Language Models: A Survey](https://mlsanity.com/paper/2410.02650/) (2024)
- [The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling](https://mlsanity.com/paper/2410.09223/) (2024)
- [Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks](https://mlsanity.com/paper/2407.04690/) (2024)
- [Controllable Context Sensitivity and the Knob Behind It](https://mlsanity.com/paper/2411.07404/) (2024)
- [How Do Vision-Language Models Process Conflicting Information Across Modalities?](https://mlsanity.com/paper/2507.01790/) (2025)
- [Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience](https://mlsanity.com/paper/2406.01352/) (2024)
- [ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.15543/) (2025)
- [The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation](https://mlsanity.com/paper/2505.15807/) (2025)
- [When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models](https://mlsanity.com/paper/2507.13868/) (2025)
- [Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models](https://mlsanity.com/paper/2509.24156/) (2025)
- [ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains](https://mlsanity.com/paper/2410.09870/) (2024)
- [Whither symbols in the era of advanced neural networks?](https://mlsanity.com/paper/2508.05776/) (2025)
- [Analyzing limits for in-context learning](https://mlsanity.com/paper/2502.03503/) (2025)
- [Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.06842/) (2026)
- [Position: We Need An Algorithmic Understanding of Generative AI](https://mlsanity.com/paper/2507.07544/) (2025)
- [Dynamic Weight Grafting: Localizing Finetuned Factual Knowledge in Transformers](https://mlsanity.com/paper/2506.20746/) (2025)
- [Indications of Belief-Guided Agency and Meta-Cognitive Monitoring in Large Language Models](https://mlsanity.com/paper/2602.02467/) (2026)
- [The Generalization Ridge: Information Flow in Natural Language Generation](https://mlsanity.com/paper/2507.05387/) (2025)

## Abstract (arXiv)

Language Models (LMs) often must integrate facts they memorized in pretraining with new information that appears in a given context. These two sources can disagree, causing competition within the model, and it is unclear how an LM will resolve the conflict. On a dataset that queries for knowledge of world capitals, we investigate both distributional and mechanistic determinants of LM behavior in such situations. Specifically, we measure the proportion of the time an LM will use a counterfactual prefix (e.g., "The capital of Poland is London") to overwrite what it learned in pretraining ("Warsaw"). On Pythia and GPT2, the training frequency of both the query country ("Poland") and the in-context city ("London") highly affect the models' likelihood of using the counterfactual. We then use head attribution to identify individual attention heads that either promote the memorized answer or the in-context answer in the logits. By scaling up or down the value vector of these heads, we can control the likelihood of using the in-context answer on new data. This method can increase the rate of generating the in-context answer to 88% of the time simply by scaling a single head at runtime. Our work contributes to a body of evidence showing that we can often localize model behaviors to specific components and provides a proof of concept for how future methods might control model behavior dynamically at runtime.