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.
By Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu
As large language models (LLMs) grow more capable, they are increasingly deployed in context-rich settings where task inputs are often accompanied by long, partially irrelevant context. In a controlled setting, we find that state-of-the-art models often appear robust to task-irrelevant context at the aggregate level: prepending it to benchmark questions causes little change in overall accuracy.
Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak. We identify a key source of this failure as task insensitivity: when faced with similar but distinct tasks, models might apply patterns learned during training and fail to solve the task at hand.
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...
By Tianyu Yuan, Zhuzhong Qian
arXiv:2606. 26918v1 Announce Type: new Abstract: Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak.
By Jingyu Liu, Xiaopeng Wu, Kehan Chen, Chuan Yu, Yong Liu
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.
By MohammadReza Davari, Utkarsh Garg, Weixin Cai, Eugene Belilovsky
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.
By Ruiyang Qin, Qingzhuo Wang, Tian Wang, Zhihua Wei, Wen Shen
arXiv:2606. 05486v1 Announce Type: cross Abstract: Prompt ambiguity is a common source of failure in large language models, but is difficult to localize because it is a latent property of the prompt, while existing attribution methods are designed to explain observable outputs such as logits or generated tokens.
By Govind Ramesh, Yao Dou, Wei Xu
arXiv:2608. 05188v1 Announce Type: cross Abstract: Despite ever-increasing sophistication in language model (LM) pre- and post-training pipelines, many important failures persist: models overcondition on user framing ("sycophancy"), exhibit incomplete logical generalization, and produce confident but incorrect responses.
By Itamar Pres, Belinda Z. Li, Laura Ruis, Zifan Carl Guo, Keya Hu, Mehul Damani, Isha Puri, Ekdeep Singh Lubana, Jacob Andreas
arXiv:2507. 04221v3 Announce Type: replace-cross Abstract: We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of large language models (LLMs) without weight updates.
By Jack Lu, Ryan Teehan, Zhenbang Yang, Mengye Ren
arXiv:2609.00624v1 Announce Type: new
Abstract: A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we...
By Zeen Zhu, Zhuo Li, Weiyang Guo, Liye Zhao, Haibing Di, Yequan Wang, Jing Li
The paper presents a prompt-based method for minimal-edit grammatical error correction (GEC) that reduces overcorrection in large language models (LLMs). It introduces taxonomy-based instructions, batch prompting to regularize overcorrection, and LLM-assisted prompt optimization, achieving an $F_{0.5}$ score of 78.32 on BEA-2019 with Gemini 3.1-Pro. This approach narrows the performance gap to fine-tuned models while avoiding their infrastructure demands.
By Kateryna Karpo, Artem Chernodub