Related papers: Selective Generation for Controllable Language Mod…

Generative Artificial Intelligence (GenAI) holds a potential to advance existing educational technologies with capabilities to automatically generate personalised scaffolds that support students' self-regulated learning (SRL). While…

Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge. Such adaptation often requires iteratively improving the model toward a targeted task, yet collecting high-quality…

The ability to reason with natural language is a fundamental prerequisite for many NLP tasks such as information extraction, machine translation and question answering. To quantify this ability, systems are commonly tested whether they can…

Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their…

The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…

We present a novel approach to automatically generate non-trivial task-specific synthetic datasets for hallucination detection. Our approach features a two-step generation-selection pipeline, using hallucination pattern guidance and a…

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech. We present GenTSE, a two-stage decoder-only generative LM approach for TSE:…

Modern large language models demonstrate impressive capabilities in text generation and generalization. However, they often struggle with solving text editing tasks, particularly when it comes to correcting spelling errors and mistypings.…

Generative AI (GEN AI) models have revolutionized diverse application domains but present substantial challenges due to reliability concerns, including hallucinations, semantic drift, and inherent biases. These models typically operate as…

Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…

Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly particularly due to excessive inference latency caused by autoregressive decoding. For lossless LLM decoding…

Despite recent advancements in domain adaptation techniques for large language models, these methods remain computationally intensive, and the resulting models can still exhibit hallucination issues. Most existing adaptation methods do not…

Pretrained generative models have opened new frontiers in brain decoding by enabling the synthesis of realistic texts and images from non-invasive brain recordings. However, the reliability of such outputs remains questionable--whether they…

Aligning language models (LMs) with user intent is becoming increasingly relevant to enhance user experience. This calls for designing methods that can allow users to control the properties of the language that LMs generate, for example,…

Amidst the sharp rise in the evaluation of large language models (LLMs) on various tasks, we find that semantic textual similarity (STS) has been under-explored. In this study, we show that STS can be cast as a text generation problem while…

Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstream ranking. A key challenge is the train-serving discrepancy: pre-ranking models are trained only…

We introduce a family of multitask variational methods for semi-supervised sequence labeling. Our model family consists of a latent-variable generative model and a discriminative labeler. The generative models use latent variables to define…

A fundamental characteristic of natural language is the high rate at which speakers produce novel expressions. Because of this novelty, a heavy-tail of rare events accounts for a significant amount of the total probability mass of…

In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models. Diffusion-based generative augmentation approaches present a promising solution to this…