Related papers: Optimizing LLM Code Suggestions: Feedback-Driven T…

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Large language models (LLMs) are increasingly used for high-stakes decision-making, yet existing approaches struggle to reconcile scalability, interpretability, and reproducibility. Black-box models obscure their reasoning, while recent…

Efficient scheduling is crucial for interactive Large Language Model (LLM) applications, where low request completion time directly impacts user engagement. Size-based scheduling algorithms like Shortest Remaining Process Time (SRPT) aim to…

Large language models (LLMs) are now used in multi-turn workflows, but we still lack a clear way to measure when iteration helps and when it hurts. We present an evaluation framework for iterative refinement that spans ideation, code, and…

Conventional mechanical design follows an iterative process in which initial concepts are refined through cycles of expert assessment and resource-intensive Finite Element Method (FEM) analysis to meet performance goals. While machine…

Large language models (LLMs) have been shown to exhibit a wide range of capabilities, such as writing robot code from language commands -- enabling non-experts to direct robot behaviors, modify them based on feedback, or compose them to…

The success of expanded context windows in Large Language Models (LLMs) has driven increased use of broader context in retrieval-augmented generation. We investigate the use of LLMs for retrieval augmented question answering. While longer…

We introduce a novel paradigm in compiler optimization powered by Large Language Models with compiler feedback to optimize the code size of LLVM assembly. The model takes unoptimized LLVM IR as input and produces optimized IR, the best…

Large Language Models (LLMs) have seen great advance in both academia and industry, and their popularity results in numerous open-source frameworks and techniques in accelerating LLM pre-training, fine-tuning, and inference. Training and…

Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…

Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts fed to LLMs…

Large Language Models (LLMs) have demonstrated remarkable adaptability, showcasing their capacity to excel in tasks for which they were not explicitly trained. However, despite their impressive natural language processing (NLP)…

Data augmentation is a critical component of deep learning pipelines, enhancing model generalization by increasing dataset diversity. Traditional augmentation strategies rely on manually designed transformations, stochastic sampling, or…

Contemporary recommendation systems predominantly rely on ID embedding to capture latent associations among users and items. However, this approach overlooks the wealth of semantic information embedded within textual descriptions of items,…

Large language models (LLMs) are increasingly used in social science simulations. While their performance on reasoning and optimization tasks has been extensively evaluated, less attention has been paid to their ability to simulate human…

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

This paper aims to address the challenge of sparse and missing data in recommendation systems, a significant hurdle in the age of big data. Traditional imputation methods struggle to capture complex relationships within the data. We propose…

Difficulty spillover and suboptimal help-seeking challenge the sequential, knowledge-intensive nature of digital tasks. In online surveys, tough questions can drain mental energy and hurt performance on later questions, while users often…

Large Language Models (LLMs) are increasingly applied to automate software engineering tasks, including the generation of UML class diagrams from natural language descriptions. While prior work demonstrates that LLMs can produce…