arXiv:2606. 04057v1 Announce Type: cross Abstract: Large language models (LLMs) now generate substantial production code, often for tasks with multiple valid algorithmic solutions.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
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:2603. 23530v2 Announce Type: replace-cross Abstract: Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks.
arXiv:2604. 22027v2 Announce Type: replace-cross Abstract: One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the question is posed.
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.
arXiv:2606. 12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs.
Narcissus is a program synthesizer that uses context‑aware large language model (LLM) approximations to guide enumerative search. Unlike prior methods that convert LLM proposals into rule frequencies and lose structural information, Narcissus retains proposals as syntax trees and scores each program expansion based on its surrounding context, ensuring every rule remains reachable. Across five domains and two search backends, it consistently outperforms static guidance and LLM re‑prompting, solving 40% of ARC tasks that raw proposals only solve 13%, all without any LLM calls during search.