LLMbench supplies a side-by-side workbench with probability overlays and variation modes that treat LLM output as a research object whose counterfactual history is made legible.
Probs” in the Compare toolbar re-sends the current prompt to the model API and requests what is called “logprob
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLMbench: A Comparative Close Reading Workbench for Large Language Models
LLMbench supplies a side-by-side workbench with probability overlays and variation modes that treat LLM output as a research object whose counterfactual history is made legible.