Related papers: Dialz: A Python Toolkit for Steering Vectors

We introduce a novel software abstraction termed "model caller," acting as an intermediary for AI and ML model calling, advocating its transformative utility beyond existing model-serving frameworks. This abstraction offers multiple…

In this paper, we introduce DiarizationLM, a framework to leverage large language models (LLM) to post-process the outputs from a speaker diarization system. Various goals can be achieved with the proposed framework, such as improving the…

Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model…

Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…

This paper presents a novel evaluation approach to text-based speaker diarization (SD), tackling the limitations of traditional metrics that do not account for any contextual information in text. Two new metrics are proposed, Text-based…

Large language models (LLMs) support data analysis through conversational user interfaces, as exemplified in OpenAI's ChatGPT (formally known as Advanced Data Analysis or Code Interpreter). Essentially, LLMs produce code for accomplishing…

Recent works have shown the power of linear indexed type systems for enforcing complex program properties. These systems combine linear types with a language of type-level indices, allowing more fine-grained analyses. Such systems have been…

We present PyNeuralFx, an open-source Python toolkit designed for research on neural audio effect modeling. The toolkit provides an intuitive framework and offers a comprehensive suite of features, including standardized implementation of…

Over the past decade, scientific studies have used the growing availability of large tracking datasets to enhance our understanding of human mobility behavior. However, so far data processing pipelines for the varying data collection…

Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data…

Discrete Diffusion Language Models (DLMs) offer a promising non-autoregressive alternative for text generation, yet effective mechanisms for inference-time control remain relatively underexplored. Existing approaches include sampling-level…

Exploratory visual data analysis tools empower data analysts to efficiently and intuitively explore data insights throughout the entire analysis cycle. However, the gap between common programmatic analysis (e.g., within computational…

Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various…

Dataset distillation aims to compress a training dataset by creating a small number of informative synthetic samples such that neural networks trained on them perform as well as those trained on the original training dataset. Current text…

The Planning Domain Definition Language (PDDL) is the state-of-the-art language for specifying planning problems in artificial intelligence research. Writing and maintaining these planning problems, however, can be time-consuming and error…

Large language models (LLMs) often struggle with mathematical problems that require exact computation or multi-step algebraic reasoning. Tool-integrated reasoning (TIR) offers a promising solution by leveraging external tools such as code…

Behavioral studies using personal digital devices typically produce rich longitudinal datasets of mixed data types. These data provide information about the behavior of users of these devices in real-time and in the users' natural…

Large Language Models (LLMs) have emerged as powerful tools for generating coherent text, understanding context, and performing reasoning tasks. However, they struggle with temporal reasoning, which requires processing time-related…

Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniques address this problem by adding a domain invariant…

Large Language Models (LLMs) have become ubiquitous in everyday life and are entering higher-stakes applications ranging from summarizing meeting transcripts to answering doctors' questions. As was the case with earlier predictive models,…