Related papers: Correct and Optimal: the Regular Expression Infere…

Many applied settings in empirical economics involve simultaneous estimation of a large number of parameters. In particular, applied economists are often interested in estimating the effects of many-valued treatments (like teacher effects…

The rapid escalation from elementary school-level to frontier problems of the difficulty for LLM benchmarks in recent years have weaved a miracle for researchers that we are only inches away from surpassing human intelligence. However, is…

While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling…

We introduce a novel theoretical framework for Return On Investment (ROI) maximization in repeated decision-making. Our setting is motivated by the use case of companies that regularly receive proposals for technological innovations and…

Widespread adoption of AI systems hinges on their ability to generate economic value that outweighs their inference costs. Evaluating this tradeoff requires metrics accounting for both performance and costs. Building on production theory,…

Reinforcement Learning (RL) for training Large Language Models is notoriously unstable. While recent studies attribute this to "training inference mismatch stemming" from inconsistent hybrid engines, standard remedies, such as Importance…

Inverse reinforcement learning (IRL) usually assumes the reward function model is pre-specified as a weighted sum of features and estimates the weighting parameters only. However, how to select features and determine a proper reward model…

The successful application of machine learning (ML) methods becomes increasingly dependent on their interpretability or explainability. Designing explainable ML systems is instrumental to ensuring transparency of automated decision-making…

Model merging has shown that multitask models can be created by directly combining the parameters of different models that are each specialized on tasks of interest. However, models trained independently on distinct tasks often exhibit…

[Context] The lack of practical relevance in many Software Engineering (SE) research contributions is often rooted in oversimplified views of industrial practice, weak industry connections, and poorly defined research problems. Clear…

Large Language Models (LLMs) have exhibited strong mathematical reasoning prowess, tackling tasks ranging from basic arithmetic to advanced competition-level problems. However, frequently occurring subtle yet critical errors, such as…

Reinforcement learning (RL) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs), as evidenced by recent successes such as OpenAI's o1 and Deepseek-R1. However, applying RL at scale remains…

As prompt engineering research rapidly evolves, evaluations beyond accuracy are crucial for developing cost-effective techniques. We present the Economical Prompting Index (EPI), a novel metric that combines accuracy scores with token…

The ability of neural networks to perform robotic perception and control tasks such as depth and optical flow estimation, simultaneous localization and mapping (SLAM), and automatic control has led to their widespread adoption in recent…

Reinforcement learning (RL) problems are fundamental in online decision-making and have been instrumental in finding an optimal policy for Markov decision processes (MDPs). Function approximations are usually deployed to handle large or…

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Pruning at initialization (PaI) reduces training costs by removing weights before training, which becomes increasingly crucial with the growing network size. However, current PaI methods still have a large accuracy gap with iterative…

Relation extraction (RE) is an indispensable information extraction task in several disciplines. RE models typically assume that named entity recognition (NER) is already performed in a previous step by another independent model. Several…

Large Language Models (LLMs) have exhibited remarkable capabilities across diverse domains, prompting investigations into their potential as generic reasoning engines. While recent studies have explored inference-time computation to enhance…

Assessing the quality of outputs generated by generative models, such as large language models and vision language models, presents notable challenges. Traditional methods for evaluation typically rely on either human assessments, which are…