What a Word Limit Removes: Length Constraints Look Free, Costly or Helpful Depending on the Span They Bind, the Scorer That Reads the Answer and the Items Chosen, and Why Compliance Looks Orthogonal to Accuracy in Only One Kind of Design

2026-10-25T10:31:37Z https://lifeofresearch.com/oai2

oai:lifeofresearch.com:136 2026-10-25T08:31:05Z type:preprint openaire

10.5281/zenodo.23628985 https://lifeofresearch.com/preprints/136 Pranay Mahendrakar 0009-0003-7224-029X SONYTECH What a Word Limit Removes: Length Constraints Look Free, Costly or Helpful Depending on the Span They Bind, the Scorer That Reads the Answer and the Items Chosen, and Why Compliance Looks Orthogonal to Accuracy in Only One Kind of Design Life of Research 2026 length constraints instruction following conciseness chain-of-thought compression verbosity bias LLM-as-a-judge evaluation methodology measurement validity Preprint Creative Commons Attribution 4.0 (c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. Life of Research Published work on telling a language model to be brief disagrees about almost everything. One benchmark reports that obeying a word limit and answering accurately are statistically unrelated, and that alignment for helpfulness is what makes models overrun the limit. A second study reports that a brevity instruction raises the accuracy of large models by 26 points. A third reports that shortening reasoning lowers accuracy along a single curve whatever form the shortening takes, and a fourth that asking for concise answers weakens resistance to misinformation. In this analysis the author reviews and synthesises published results to show that these findings are compatible once three things are stated that the studies usually leave implicit: which span of text the limit binds (the prompt, the reasoning, or the answer), which scoring rule reads the shortened output, and which items the comparison was run on. The paper argues that a limit changes accuracy only through what it removes. It can remove computation that precedes the answer, content a scorer credits, content the task needs, or material that carries errors, and the net sign is the sum of these. Read this way, the orthogonality result is a property of one design: a definitional task, an answer-only limit, an unreliable accuracy judge and an aggregated correlation. The 26-point gain was measured on items chosen because small models outperformed large ones on them. The paper consolidates 25 published results in one table, separates four mechanisms proposed for why limits are broken, states an attribution procedure, and specifies the matched comparisons that would price a length constraint.