Related papers: Which Discriminator for Cooperative Text Generatio…
The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or…
Building effective text generation systems requires three critical components: content selection, text planning, and surface realization, and traditionally they are tackled as separate problems. Recent all-in-one style neural generation…
We propose Future Discriminators for Generation (FUDGE), a flexible and modular method for controlled text generation. Given a pre-existing model G for generating text from a distribution of interest, FUDGE enables conditioning on a desired…
Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained…
Deep learning classifiers are prone to latching onto dominant confounders present in a dataset rather than on the causal markers associated with the target class, leading to poor generalization and biased predictions. Although…
Language Generation Models produce words based on the previous context. Although existing methods offer input attributions as explanations for a model's prediction, it is still unclear how prior words affect the model's decision throughout…
Language generation models' democratization benefits many domains, from answering health-related questions to enhancing education by providing AI-driven tutoring services. However, language generation models' democratization also makes it…
Many natural language related applications involve text generation, created by humans or machines. While in many of those applications machines support humans, yet in few others, (e.g. adversarial machine learning, social bots and trolls)…
The meteoric rise in text generation capability has been accompanied by parallel growth in interest in machine-generated text detection: the capability to identify whether a given text was generated using a model or written by a person.…
We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from "neighbor" source-target pairs. Unlike recent work that conditions on retrieved neighbors but generates text token-by-token,…
SemEval-2024 Task 8 introduces the challenge of identifying machine-generated texts from diverse Large Language Models (LLMs) in various languages and domains. The task comprises three subtasks: binary classification in monolingual and…
We analyze various methods for single-label and multi-label text classification across well-known datasets, categorizing them into bag-of-words, sequence-based, graph-based, and hierarchical approaches. Despite the surge in methods like…
The automated categorization (or classification) of texts into predefined categories has witnessed a booming interest in the last ten years, due to the increased availability of documents in digital form and the ensuing need to organize…
This paper focuses on Code Generation task that aims at generating relevant code fragments according to given natural language descriptions. In the process of software development, developers often encounter two scenarios. One is requested…
Generative models defining joint distributions over parse trees and sentences are useful for parsing and language modeling, but impose restrictions on the scope of features and are often outperformed by discriminative models. We propose a…
Recent literature highlights the critical role of neighborhood construction in deriving model-agnostic explanations, with a growing trend toward deploying generative models to improve synthetic instance quality, especially for explaining…
Existing large language model-based code generation pipelines typically use beam search or sampling algorithms during the decoding process. Although the programs they generate achieve high token-matching-based scores, they often fail to…
Past work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or off-the-shelf models to first tag training stories with the…
Asking good questions in large-scale, open-domain conversational systems is quite significant yet rather untouched. This task, substantially different from traditional question generation, requires to question not only with various patterns…
Generative models achieve remarkable results in multiple data domains, including images and texts, among other examples. Unfortunately, malicious users exploit synthetic media for spreading misinformation and disseminating deepfakes.…