SPIN Unprocessed October 28, 2026 ai_technology research
3, 7, 14, 17, 42: Instruction Tuning Installs and Sharpens Number-Choice Heuristics in Language Models
View original on arxiv.orgOverview
arXiv:2610.36178v1 Announce Type: new Abstract: We measure, without sampling error, the probability a language model assigns to each integer from 1 to N when asked for a random number. For a fixed prompt the model defines one probability vector, which we compute by summing over each integer's scored spellings rather than estimate by sampling, removing the noise that limits earlier studies [1, 4]. We evaluate 18 open-weight model lines at five ranges up to N = 100, under 29 decoding configuration
SpinGraph analysis pending — check back after processing.
Ask AI about this story
Opens with the SpinGraph .md URL and structured context — one click, prompt included.
More from arXiv Computation and Language
View all →- Japanese Discourse Structure Analysis Based on Segmented Discourse Representation Theory Using LLMs
- Structured Maps for Landmark-Based Route Instructions with LLMs
- Agentic Data Sampling Framework for Multilingual ASR via Linguistic-Aware Error-Driven Optimization
- ETC-Bench: A Multilingual Benchmark for Evaluation-Side Transcript Canonicalization
- Causal Localization of Evidence Effects in Transformers
- Benchmarking Task Takeover Across Agent Handoffs
Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO