prompt-robustness

Tag

Cards List
#prompt-robustness

Prompt Robustness Is Task-Dependent: Comparing Objective and Belief-Style Questions in LLM Evaluation

arXiv cs.CL · 2026-07-08 Cached

This paper investigates how prompt robustness varies between objective and subjective questions in LLM evaluations, finding that sensitivity to prompt changes depends on question type, prompt change, and model.

0 favorites 0 likes
#prompt-robustness

One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation

arXiv cs.CL · 2026-05-22 Cached

This paper empirically demonstrates that single-prompt evaluation of instruction-tuned embedding models is insufficient, as performance varies significantly with prompt phrasing and leaderboard rankings can be manipulated by prompt selection.

0 favorites 0 likes
← Back to home

Submit Feedback