Related papers: Improving abcdSAT by At-Least-One Recently Used Cl…
Large Language Models (LLMs) have shown superior performance in various applications and fields. To achieve better performance on specialized domains such as law and advertisement, LLMs are often continue pre-trained on in-domain data.…
We apply the splitting method to three well-known counting problems, namely 3-SAT, random graphs with prescribed degrees, and binary contingency tables. We present an enhanced version of the splitting method based on the capture-recapture…
A wide range of constraints can be compactly specified using automata or formal languages. In a sequence of recent papers, we have shown that an effective means to reason with such specifications is to decompose them into primitive…
In-context Learning (ICL) utilizes structured demonstration-query inputs to induce few-shot learning on Language Models (LMs), which are not originally pre-trained on ICL-style data. To bridge the gap between ICL and pre-training, some…
Automated audio captioning (AAC) aims to generate informative descriptions for various sounds from nature and/or human activities. In recent years, AAC has quickly attracted research interest, with state-of-the-art systems now relying on a…
Over the past few years, we have witnessed remarkable advancements in Code Pre-trained Models (CodePTMs). These models achieved excellent representation capabilities by designing structure-based pre-training tasks for code. However, how to…
Dataset shift is common in credit scoring scenarios, and the inconsistency between the distribution of training data and the data that actually needs to be predicted is likely to cause poor model performance. However, most of the current…
In this study, we present an incremental machine learning framework called Adaptive Decision Forest (ADF), which produces a decision forest to classify new records. Based on our two novel theorems, we introduce a new splitting strategy…
Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024). In this work we…
Although railway dispatching on large national networks is gradually becoming more computerized, there are still major obstacles to retrofitting (semi-)autonomous control systems. In addition to requiring extensive and detailed…
The Satisfiability (SAT) problem is a core challenge with significant applications in software engineering, including automated testing, configuration management, and program verification. This paper presents SolSearch, a novel framework…
Automatic Arabic diacritization is useful in many applications, ranging from reading support for language learners to accurate pronunciation predictor for downstream tasks like speech synthesis. While most of the previous works focused on…
Online Convex Optimization plays a key role in large scale machine learning. Early approaches to this problem were conservative, in which the main focus was protection against the worst case scenario. But recently several algorithms have…
Automatic summarization of legal texts is an important and still a challenging task since legal documents are often long and complicated with unusual structures and styles. Recent advances of deep models trained end-to-end with…
Recently, pre-trained language models (LMs) have achieved strong performance when fine-tuned on difficult benchmarks like SuperGLUE. However, performance can suffer when there are very few labeled examples available for fine-tuning. Pattern…
We consider the problem of solving floating-point constraints obtained from software verification. We present UppSAT --- a new implementation of a systematic approximation refinement framework [ZWR17] as an abstract SMT solver. Provided…
Dates and calendar periods (i.e., days, months, years) appear frequently in tasks involving analysis of software, data, and documents. Prior research has shown that computer logic involving dates and calendrical calculations is error-prone…
We consider the Adaptive Regularization with Cubics approach for solving nonconvex optimization problems and propose a new variant based on inexact Hessian information chosen dynamically. The theoretical analysis of the proposed procedure…
Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…
To create models that are robust across a wide range of test inputs, training datasets should include diverse examples that span numerous phenomena. Dynamic adversarial data collection (DADC), where annotators craft examples that challenge…