Related papers: Linearly Controlled Language Generation with Perfo…

We propose a method to fuse frozen text-only large language models (LLMs) with pre-trained image encoder and decoder models, by mapping between their embedding spaces. Our model demonstrates a wide suite of multimodal capabilities: image…

As Large Language Models (LLMs) are deployed more widely, customization with respect to vocabulary, style, and character becomes more important. In this work, we introduce model arithmetic, a novel inference framework for composing and…

Many neural network models nowadays have achieved promising performances in Chit-chat settings. The majority of them rely on an encoder for understanding the post and a decoder for generating the response. Without given assigned semantics,…

Citation generation aims to generate a citation sentence that refers to a chosen paper in the context of a manuscript. However, a rigid citation generation process is at odds with an author's desire to control specific attributes, such as…

Fine-tuning LLM-based text embedders via contrastive learning maps inputs and outputs into a new representational space, discarding the LLM's output semantics. We propose LLM2Vec-Gen, a self-supervised alternative that instead produces…

While large language models (LLMs) have made significant strides in generating coherent and contextually relevant text, they often function as opaque black boxes, trained on vast unlabeled datasets with statistical objectives, lacking an…

Transformer-based Large Language Models (LLMs) have shown exceptional language generation capabilities in response to text-based prompts. However, controlling the direction of generation via textual prompts has been challenging, especially…

In this article we show how the problem of neural text generation can be constructively reformulated in terms of transitions between the states of a finite-state machine. This framework leads to an efficient approach to guiding text…

Text Generation aims to produce plausible and readable text in a human language from input data. The resurgence of deep learning has greatly advanced this field, in particular, with the help of neural generation models based on pre-trained…

LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for many tasks. The current established technology of LLMs is to process input and generate output at the token level. This is in sharp…

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are crucial for a successful dialogue, it is also desirable to…

Pretrained Transformer-based language models (LMs) display remarkable natural language generation capabilities. With their immense potential, controlling text generation of such LMs is getting attention. While there are studies that seek to…

Text generation has become one of the most important yet challenging tasks in natural language processing (NLP). The resurgence of deep learning has greatly advanced this field by neural generation models, especially the paradigm of…

We propose a Distributional Approach for addressing Controlled Text Generation from pre-trained Language Models (LMs). This approach permits to specify, in a single formal framework, both "pointwise" and "distributional" constraints over…

Text generation aims to produce human-like natural language output for down-stream tasks. It covers a wide range of applications like machine translation, document summarization, dialogue generation and so on. Recently deep neural…

Steering language generation towards objectives or away from undesired content has been a long-standing goal in utilizing language models (LM). Recent work has demonstrated reinforcement learning and weighted decoding as effective…

Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to…

Controllable and transparent text generation has been a long-standing goal in NLP. Almost as long-standing is a general idea for addressing this challenge: Parsing text to a symbolic representation, and generating from it. However, earlier…

This work aims to employ natural language generation (NLG) to rapidly generate items for English language learning applications: this requires both language models capable of generating fluent, high-quality English, and to control the…