Back to search

Article

Protocol-Dependent Resolution in Finite-Sample Model Selection

2026-08-19

Abstract excerpt

<title>Abstract</title> <p>The maximum number of tokens a model is allowed to generate can reverse whether a set of checkpoints looks distinguishable or indistinguishable, and can hide a strong negative trend (ρ = −0.77) behind apparently flat performance. We document this through controlled LoRA experi- ments (Qwen2.5-7B, Mistral-7B) where moving from 128 to 256 tokens shifts accuracy ranges by 2.3×, flips pairw...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
399596ae-c491-5379-becd-85e59d3cc319
DOI
10.21203/rs.3.rs-10469456/v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Protocol-Dependent Resolution in Finite-Sample Model SelectionDOI 10.21203/rs.3.rs-10469456/v1
Select a neighboring publication to make it the new centre.