Fabricator or dynamic translator?
LLMs are proving to be adept at machine translation although due to their generative nature they may at times overgenerate in various ways. These overgenerations are different from the neurobabble seen in NMT and range from LLM self-explanations, to risky confabulations, to appropriate explanations, where the LLM is able to act as a human translator would, enabling greater comprehension for the target audience. Detecting and determining the exact nature of the overgenerations is a challenging task. We detail different strategies we have explored for our work in a commercial setting, and present our results.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationSimilar Papers 제목 키워드 기반
Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs
Most NLP tasks are modeled as supervised learning and thus require labeled training data to train effective models. However, manually producing such data at sufficient quality and quantity is known to be costly and time-…
Dataset GenerationQuestion Answeringtext-classificationText Classification+1Fill in Fabrics: Body-Aware Self-Supervised Inpainting for Image-Based Virtual Try-On
Previous virtual try-on methods usually focus on aligning a clothing item with a person, limiting their ability to exploit the complex pose, shape and skin color of the person, as well as the overall structure of the clo…
Generative Adversarial NetworkVirtual Try-onDetecting Human-Object Interaction via Fabricated Compositional Learning
Human-Object Interaction (HOI) detection, inferring the relationships between human and objects from images/videos, is a fundamental task for high-level scene understanding. However, HOI detection usually suffers from th…
Affordance RecognitionHuman-Object Interaction DetectionObjectScene UnderstandingMulti-species consensus network of DNA strand displacement for concentration-to-strand translation
We propose novel chemical reaction networks to translate levels of concentration into unique DNA strand species, which we call concentration translators. Our design of the concentration translators is based on combinatio…
TranslationProgressive Energy-Based Cooperative Learning for Multi-Domain Image-to-Image Translation
This paper studies a novel energy-based cooperative learning framework for multi-domain image-to-image translation. The framework consists of four components: descriptor, translator, style encoder, and style generator. T…
Image-to-Image Translation