2026-05-22 04:00 UTCOriginal source2 min readUpdated: 2026-06-30 13:03 UTC

Does Slightly Mean Somewhat? Measuring Vague Intensity Words in LLM Numeric Actions

A controlled study finds that Claude Haiku compresses 10 English intensity words into 5 distinct median outputs, with the model’s interpretation heavily dependent on system state, and displays three behavioral modes near feasibility limits.

SourcearXiv Computational LinguisticsAuthor: Daniel Tabach (Georgia Institute of Technology)

Article intelligence

EngineersAdvanced

Key points

The model compresses 10 intensity words into 5 distinct median outputs; four lower-tier words map to the same value.
System state influences numeric output far more than word choice, explaining 78.2% of rank variance versus 7.9% for words.
Near capacity limits, weak words hedge with small adjustments, strong words abstain entirely, and 'drastically' pushes to the local ceiling.
Temperature broadens distributions but does not restore ordinal distinctions between words.

Why it matters

This matters because the model compresses 10 intensity words into 5 distinct median outputs; four lower-tier words map to the same value.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

This panel is AI-generated and reviewed for accuracy.

[2605.21827] Does Slightly Mean Somewhat? Measuring Vague Intensity Words in LLM Numeric Actions

[Submitted on 20 May 2026]

Title:Does Slightly Mean Somewhat? Measuring Vague Intensity Words in LLM Numeric Actions

View a PDF of the paper titled Does Slightly Mean Somewhat? Measuring Vague Intensity Words in LLM Numeric Actions, by Daniel Tabach (Georgia Institute of Technology)

View PDF HTML (experimental)

Abstract:Do language models preserve the ordinal meaning of intensity words when those words must produce numeric actions? I study a researcher-constructed scale of 10 English degree modifiers, from slightly to drastically, informed by the Quirk et al. degree-modifier taxonomy, in a controlled resource-allocation environment where Claude Haiku receives a natural-language instruction, produces a numeric allocation, and a deterministic backend converts that allocation into a measurable outcome. The only variable that changes between runs is the intensity word or the starting system state, isolating their effects on the model's numeric output.

Across 6,620 runs at T=0.0 and T=0.7, three patterns emerge. First, the model compresses 10 intensity words into 5 distinct median outputs: four lower-tier words all map to the same value, while stronger words break into higher regimes (Spearman rho = 0.845, p

new | recent | 2026-05

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)