相关论文: Which Discriminator for Cooperative Text Generatio…

With the advent of fluent generative language models that can produce convincing utterances very similar to those written by humans, distinguishing whether a piece of text is machine-generated or human-written becomes more challenging and…

Most existing text generation models follow the sequence-to-sequence paradigm. Generative Grammar suggests that humans generate natural language texts by learning language grammar. We propose a syntax-guided generation schema, which…

Security classifiers, designed to detect malicious content in computer systems and communications, can underperform when provided with insufficient training data. In the security domain, it is often easy to find samples of the negative…

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…

Typical text recognition methods rely on an encoder-decoder structure, in which the encoder extracts features from an image, and the decoder produces recognized text from these features. In this study, we propose a simpler and more…

Despite considerable advancements with deep neural language models, the enigma of neural text degeneration persists when these models are tested as text generators. The counter-intuitive empirical observation is that even though the use of…

While recent advances in language modeling have resulted in powerful generation models, their generation style remains implicitly dependent on the training data and can not emulate a specific target style. Leveraging the generative…

Bias detection in text is crucial for combating the spread of negative stereotypes, misinformation, and biased decision-making. Traditional language models frequently face challenges in generalizing beyond their training data and are…

With the popularity of automatic code generation tools, such as Copilot, the study of the potential hazards of these tools is gaining importance. In this work, we explore the social bias problem in pre-trained code generation models. We…

As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a…

The knowledge of source printer can help in printed text document authentication, copyright ownership, and provide important clues about the author of a fraudulent document along with his/her potential means and motives. Development of…

It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllable text generation,…

The pattern theory of Grenander is a mathematical framework where patterns are represented by probability models on random variables of algebraic structures. In this paper, we review three families of probability models, namely, the…

Current language models achieve low perplexity but their resulting generations still suffer from toxic responses, repetitiveness and contradictions. The standard language modeling setup fails to address these issues. In this paper, we…

Considering that words with different characteristic in the text have different importance for classification, grouping them together separately can strengthen the semantic expression of each part. Thus we propose a new text representation…

Text classification helps analyse texts for semantic meaning and relevance, by mapping the words against this hierarchy. An analysis of various types of texts is invaluable to understanding both their semantic meaning, as well as their…

Large language models (LLMs) have reached human-like proficiency in generating diverse textual content, underscoring the necessity for effective fake text detection to avoid potential risks such as fake news in social media. Previous…

Due to the discrete nature of words, language GANs require to be optimized from rewards provided by discriminator networks, via reinforcement learning methods. This is a much harder setting than for continuous tasks, which enjoy gradient…

Recently, high-performing code generation systems based on large language models have surfaced. They are trained on massive corpora containing much more natural text than actual executable computer code. This work shows that current code…

Detecting tampered text in document images is a challenging task due to data scarcity. To address this, previous work has attempted to generate tampered documents using rule-based methods. However, the resulting documents often suffer from…