Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support. This gap is commonly attributed to retrieval failures—the models’ inability to identify information in the long inputs that is relevant to the task they are solving. Accordingly, recent efforts often focus on evaluating and improving LLMs’ retrieval performance: if retrieval is perfect, a model should, in principle, perform just as well on a long input as it does on a short one—or should it? This paper presents findings that the answer to this question may be negative. Our systematic experiments across 5 open- and closed-source LLMs on math, question answering, and coding tasks reveal that, even when models can perfectly retrieve all relevant information, their performance still degrades substantially (13.9%–85%) as input length increases but remains well within their claimed context lengths. This failure occurs even when the irrelevant tokens are replaced with minimally distracting whitespace, and, more surprisingly, when they are all masked and the models are forced to attend only to the relevant tokens. A similar performance drop is observed when all relevant evidence is placed immediately before the question. Our findings reveal a previously-unrealized limitation: the sheer length of the input alone can hurt LLM performance, independent of retrieval quality and without any distraction. They motivate our simple, model-agnostic mitigation strategy that transforms a long-context task into a short-context one by prompting the model to recite the retrieved evidence before attempting to solve the problem. On RULER, we observe a consistent improvement of GPT-4o up to 4% on an already strong baseline.

Extraction of experimental procedures from human language in scientific literature and patents into actionable sequences in robotics language holds immense significance in scientific domains. Such an action extraction task is particularly challenging given the intricate details and context-dependent nature of the instructions, especially in fields like chemistry where reproducibility is paramount. In this paper, we introduce ActionIE, a method that leverages Large Language Models (LLMs) to bridge this divide by converting actions written in natural language into executable Python code. This enables us to capture the entities of interest, and the relationship between each action, given the features of Programming Languages. Utilizing linguistic cues identified by frequent patterns, ActionIE provides an improved mechanism to discern entities of interest. While our method is broadly applicable, we exemplify its power in the domain of chemical literature, wherein we focus on extracting experimental procedures for chemical synthesis. The code generated by our method can be easily transformed into robotics language which is in high demand in scientific fields. Comprehensive experiments demonstrate the superiority of our method. In addition, we propose a graph-based metric to more accurately reflect the precision of extraction. We also develop a dataset to address the scarcity of scientific literature occurred in existing datasets.