The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models
A recent study explores the effectiveness of chain-of-thought (CoT) prompting in small language models for arithmetic tasks. The research identifies a positional shortcut where models tend to copy the last number before the answer delimiter, significantly impacting accuracy. This finding raises questions about the genuine computational capabilities of these models when using CoT prompting.
- ▪The study focuses on small language models with 1-3 billion parameters.
- ▪It finds that models often copy the last number before the answer delimiter, affecting their performance.
- ▪Accuracy can drop to near-zero if the trailing number is incorrect, despite correct intermediate reasoning.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.22870 |
| Publication time | Mon, 25 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-25T04:07:35.648Z |
| Last seen | 2026-05-25T04:07:35.648Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 2o2NmVN80nLY |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Machine Learning arXiv:2605.22870 (cs) [Submitted on 20 May 2026] Title:The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models Authors:Ming Liu View a PDF of the paper titled The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models, by Ming Liu View PDF HTML (experimental) Abstract:Chain-of-thought (CoT) prompting is necessary for arithmetic in small language models, yet shuffling its steps preserves most performance.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
