arXiv:2511. 19829v3 Announce Type: replace Abstract: Prompt optimization has become a central mechanism for eliciting strong performance from LLMs, and recent work has made substantial progress by proposing diverse prompt evaluation metrics and optimization strategies.
arXiv:2511. 19829v2 Announce Type: replace Abstract: Most prompt-optimization methods refine a single static template, making them ineffective in complex and dynamic user scenarios.
arXiv:2507. 09839v2 Announce Type: replace Abstract: An increasing number of NLP applications interact with large language models (LLMs) through black-box APIs, making prompt engineering critical for controlling model behavior.
arXiv:2609.39927v1 Announce Type: new Abstract: Prompt optimization improves the performance of language-model systems on downstream tasks by refining their prompts. Classical methods evaluate prompt...
The paper investigates how small lexical changes in prompts can cause large performance swings in large language models. Using a dataset of 132,000 prompt variants, the authors uncover a scaling law linking higher average task performance to lower variance and greater robustness. They identify domain-specific terminology and explicit action directives as key linguistic factors that stabilize prompts, and propose an automated Prompt-Refining Agent that reduces performance variance by 40.7% in code generation while maintaining or improving mean performance.
arXiv:2606. 11459v1 Announce Type: cross Abstract: Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential.
arXiv:2606. 27226v1 Announce Type: new Abstract: Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug.
arXiv:2609.15209v1 Announce Type: cross Abstract: Automatic prompt optimization (APO) improves language-model programs by revising prompts from task feedback, yet it typically holds its training data...
The paper introduces a fine-grained method called interactions to analyze prompt sensitivity in large language models (LLMs). By decomposing output scores into nonlinear interactions, the authors show that subtle prompt changes can destabilize these interactions even when overall outputs stay unchanged. They propose an Interaction-based Prompt Sensitivity (IPS) metric and use it to evaluate 50 open-source LLMs, finding that supervised fine‑tuning, larger model scales, dense architectures, and few‑shot learning all reduce prompt sensitivity, primarily by stabilizing low‑order interactions.
Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug. We propose BINEVAL, a framework that decomposes evaluation criteria into atomic binary questions and aggregates the resulting verdicts into interpretable, multi-dimensional scores.
arXiv:2607. 14105v1 Announce Type: cross Abstract: For Large Language Models to reliably answer user queries, users must clearly specify requirements, context, and constraints.
arXiv:2609.21626v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for enterprise information extraction (IE), where the same document must be reorganized differen...
arXiv:2607. 21756v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in database-backed applications to classify tuples, filter records using semantic predicates, extract structured attributes, and enrich query results.