Related papers: Sublinear Risk-Limiting Audits from Direct Ballot …
Production LLM systems increasingly require machine-readable outputs: JSON objects, typed traces, regex-constrained fields, and tool-call schemas. This paper targets on-device and low-cost small language model (SLM) deployments, where…
Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…
Answering reasoning-based complex questions over text and hybrid sources, including tables, is a challenging task. Recent advances in large language models (LLMs) have enabled in-context learning (ICL), allowing LLMs to acquire proficiency…
The ability to rigorously estimate the failure rates of large language models (LLMs) is a prerequisite for their safe deployment. Currently, however, practitioners often face a tradeoff between expensive human gold standards and potentially…
Electronic Health Records (EHRs) often lack explicit links between medications and diagnoses, making clinical decision-making and research more difficult. Even when links exist, diagnosis lists may be incomplete, especially during early…
The automation of news analysis and summarization presents a promising solution to the challenge of processing and analyzing vast amounts of information prevalent in today's information society. Large Language Models (LLMs) have…
Large language models (LLMs) have recently achieved significant success across various application domains, garnering substantial attention from different communities. Unfortunately, even for the best LLM, many \textit{faults} still exist…
The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in generating pseudo-labels…
Pretrial risk assessment tools are used on over one million U.S. defendants each year, yet their use for predicting rare violent re-offense faces a basic statistical barrier. We derive a universal precision bound -- the Likelihood Ratio…
Retrieval-augmented Generation (RAG) extends large language models (LLMs) with external knowledge but faces key challenges: restricted effective context length and redundancy in retrieved documents. Pure compression-based approaches reduce…
Learning with Noisy Labels (LNL) has become an appealing topic, as imperfectly annotated data are relatively cheaper to obtain. Recent state-of-the-art approaches employ specific selection mechanisms to separate clean and noisy samples and…
Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing approaches to improve prediction accuracy and quality…
Large language models (LLMs) frequently generate multiple candidate responses for a given prompt, yet selecting the most reliable one remains challenging, especially when correctness diverges from surface-level majority agreement. Existing…
In structured prediction problems where we have indirect supervision of the output, maximum marginal likelihood faces two computational obstacles: non-convexity of the objective and intractability of even a single gradient computation. In…
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…
The weakest pre-expectation calculus has been proved to be a mature theory to analyze quantitative properties of probabilistic and nondeterministic programs. We present an automatic method for proving quantitative linear properties on any…
Low Rank Approximation (LRA) of a matrix is a hot research subject, fundamental for Matrix and Tensor Computations and Big Data Mining and Analysis. Computations with low rank matrices can be performed at sublinear cost -- by using much…
Predicting rare outcomes such as startup success is central to venture capital, demanding models that are both accurate and interpretable. We introduce Random Rule Forest (RRF), a lightweight ensemble method that uses a large language model…
We study efficiency improvements in randomized experiments for estimating a vector of potential outcome means using regression adjustment (RA) when there are more than two treatment levels. We show that linear RA which estimates separate…
The standard voting methods in the United States, plurality and ranked choice (or instant runoff) voting, are susceptible to significant voting failures. These flaws include Condorcet and majority failures as well as monotonicity and…