The Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned Counterparts
Overview & Synopsis
We present our solution to the AKBC LM-KBC 2026 Shared Task, where we achieved a score of 0.6836 on the official leaderboard, more than double the baseline of 0.2964. This task requires generating all possible objects for subject-relation pairs using a language model with up to 32 billion parameters, with no retrieval or fine-tuning involved. We show that the prompting methodology is as important as the model architecture: while the instruction-tuned model version achieves 0.5681 with its chat interface, the base model achieves 0.6836 when prompted using text completion. Thus, instruction tuning decreases factual recall; we refer to this effect as the instruction tax, which is caused by the model's weights rather than the prompting method. Our final solution is fairly straightforward: we prompt the base model with some examples from the training data, generate 64--256 outputs, and retain only the repeated ones. Two specialized methods are then applied for each relation: one improves the recall of large answer sets, and the other verifies a person's vitality before predicting their place of death.
arxiv.org)
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | The Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned Counterparts |
|---|---|
| Author / Organization | Christophe Khalil, Aya Mourad |
| Subject & Discipline | cs.CL |
| Categories | Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-269840 |
| Original Source Link | Visit Source Page on arxiv.org » |