Related papers: Synthesizing Abstract Transformers for Reduced-Pro…
Large Language Models (LLMs), despite extensive pretraining on broad internet corpora, often struggle to adapt effectively to specialized domains. There is growing interest in fine-tuning these models for such domains; however, progress is…
Formal verification of transformers has become increasingly important due to their widespread deployment in safety-critical applications. Compared to classic neural networks, the inferences of transformers involve highly complex…
Current numerical abstract interpretation relies on fixed, hand-crafted, instruction-specific transformers tailored to each domain, causing three key limitations: transformers cannot be reused across domains; precise compositional reasoning…
Synthesis tools have seen significant success in recent times. However, past approaches often require a complete and accurate embedding of the source language in the logic of the underlying solver, an approach difficult for industrial-grade…
In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent. One common and effective strategy for this case is exploiting in-domain monolingual data with the…
Syntheto is a surface language for carrying out formally verified program synthesis by transformational refinement in ACL2 using the APT toolkit. Syntheto aims at providing more familiarity and automation, in order to make this technology…
In the domain of image processing, often real-time constraints are required. In particular, in safety-critical applications, such as X-ray computed tomography in medical imaging or advanced driver assistance systems in the automotive…
Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain. It is a challenging problem especially when a large domain gap lies between the source and target domains.…
Despite their demonstrated valuable capabilities, state-of-the-art (SOTA) widely deployed large language models (LLMs) still have the potential to cause harm to society due to the ineffectiveness of their safety filters, which can be…
In this paper, we present domain-specific languages (DSLs) that we devised for their use in the implementation of a finite domain constraint programming system, available as library(clpfd) in SWI-Prolog and YAP-Prolog. These DSLs are used…
Recent advances in automatic speech recognition (ASR) have combined speech encoders with large language models (LLMs) through projection, forming Speech LLMs with strong performance. However, adapting them to new domains remains…
We present an approach to automatically synthesize synchronized models from lightweight formal specifications. Our approach takes as input a specification of a distributed system along with a global linear time constraint, which must be…
Traditional compilers, designed for optimizing low-level code, fall short when dealing with modern, computation-heavy applications like image processing, machine learning, or numerical simulations. Optimizations should understand the…
Parameterized synthesis offers a solution to the problem of constructing correct and verified controllers for parameterized systems. Such systems occur naturally in practice (e.g., in the form of distributed protocols where the amount of…
We propose a new synthesis algorithm that can efficiently search programs with local variables (e.g., those introduced by lambdas). Prior bottom-up synthesis algorithms are not able to evaluate programs with free local variables, and…
Adapting Large Language Models (LLMs) to specialized domains requires high-quality instruction tuning datasets, which are expensive to create through human annotation. Existing data synthesis methods focus on general-purpose tasks and fail…
Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set…
The application of machine learning on tabular data in specialized domains is severely limited by data scarcity. While generative models offer a solution, traditional methods falter in low-data regimes, and recent Large Language Models…
Enhancing the mathematical reasoning of large language models (LLMs) demands high-quality training data, yet conventional methods face critical challenges in scalability, cost, and data reliability. To address these limitations, we propose…
Effective document reranking is essential for improving search relevance across diverse applications. While Large Language Models (LLMs) excel at reranking due to their deep semantic understanding and reasoning, their high computational…