# Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion

arXiv: https://arxiv.org/abs/2410.14405 · HTML: https://mlsanity.com/paper/2410.14405/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Builds on (most cited first, 23 of 23)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models](https://mlsanity.com/paper/2301.04213/) (2023)
- [Probing Neural Network Comprehension of Natural Language Arguments](https://mlsanity.com/paper/1907.07355/) (2019)
- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases](https://mlsanity.com/paper/2106.09231/) (2021)
- [E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT](https://mlsanity.com/paper/1911.03681/) (2019)
- [Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries](https://mlsanity.com/paper/2406.12775/) (2024)
- [Understanding Transformer Memorization Recall Through Idioms](https://mlsanity.com/paper/2210.03588/) (2022)
- [Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method](https://mlsanity.com/paper/2310.17918/) (2023)
- [A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia](https://mlsanity.com/paper/2312.02073/) (2023)
- [LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements](https://mlsanity.com/paper/2404.06283/) (2024)
- [Defining Knowledge: Bridging Epistemology and Large Language Models](https://mlsanity.com/paper/2410.02499/) (2024)

## Built on by (most cited first, 4 of 4)

- [CUB: Benchmarking Context Utilisation Techniques for Language Models](https://mlsanity.com/paper/2505.16518/) (2025)
- [Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queries](https://mlsanity.com/paper/2502.20475/) (2025)
- [Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity](https://mlsanity.com/paper/2608.13484/) (2026)
- [Probing Factual Knowledge Transfer with Training Data Interventions](https://mlsanity.com/paper/2609.01341/) (2026)

## Abstract (arXiv)

Language models (LMs) can make a correct prediction based on many possible signals in a prompt, not all corresponding to recall of factual associations. However, current interpretations of LMs fail to take this into account. For example, given the query "Astrid Lindgren was born in" with the corresponding completion "Sweden", no difference is made between whether the prediction was based on knowing where the author was born or assuming that a person with a Swedish-sounding name was born in Sweden. In this paper, we present a model-specific recipe - PrISM - for constructing datasets with examples of four different prediction scenarios: generic language modeling, guesswork, heuristics recall and exact fact recall. We apply two popular interpretability methods to the scenarios: causal tracing (CT) and information flow analysis. We find that both yield distinct results for each scenario. Results for exact fact recall and generic language modeling scenarios confirm previous conclusions about the importance of mid-range MLP sublayers for fact recall, while results for guesswork and heuristics indicate a critical role of late last token position MLP sublayers. In summary, we contribute resources for a more extensive and granular study of fact completion in LMs, together with analyses that provide a more nuanced understanding of how LMs process fact-related queries.