# Researchers find Instruction tuning sharpens Number-Choice heuristics in language models

Digest AI · Research · published 2026-10-28T04:00:00Z

Canonical: https://digestai.news/story/researchers-find-instruction-tuning-sharpens-number-choice-heuristics

## Summary

A new study on arXiv examines how instruction tuning affects the way language models pick numbers. The authors measured the probability of models selecting integers from 1 to N without sampling error, testing 18 open-weight model lines across five ranges up to N = 100. They found that instruction tuning reduces uniform distribution in all 15 models with matched base and tuned checkpoints, reinforcing two heuristics: avoiding round numbers and endpoints like 1 or N.

The study notes that base models do not avoid round numbers once endpoints are excluded, while tuned models nearly eliminate them. Tuned models also rarely pick endpoints, and a preference for odd numbers appears only at N = 100. The findings align partially with human number-choice behavior but differ in key ways, such as the absence of midpoint avoidance. The study concludes that tuning does not create a universal favorite number across models, as no integer exceeds 42% preference in tuned conditions.

## Key points

- Instruction tuning reduces uniform number selection in 15 of 18 tested models, reinforcing heuristics like endpoint and round-number avoidance
- Tuned models nearly eliminate round numbers and endpoints (1 or N) as choices, while base models do not show this behavior
- Preference for odd numbers appears only at N = 100, with no shared favorite integer across tuned models

## Why it matters

This research clarifies how instruction tuning influences decision-making in language models, offering insights into their biases and potential limitations in real-world applications like surveys or automated number generation.

## Sources

1. [3, 7, 14, 17, 42: Instruction Tuning Installs and Sharpens Number-Choice Heuristics in Language Models](https://arxiv.org/abs/2610.36178) (arXiv cs.CL, 2026-10-28, primary source)

## Cite

Digest AI, "Researchers find Instruction tuning sharpens Number-Choice heuristics in language models", 28 October 2026, https://digestai.news/story/researchers-find-instruction-tuning-sharpens-number-choice-heuristics

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-find-instruction-tuning-sharpens-number-choice-heuristics.json