51 citations · 83 across the 14 of their papers we have counts for
15 papers
PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks
Yunuo Liu, Dawei Zhu, Zena Al-Khalili +5
We present PricingLogic, the first benchmark that probes whether Large Language Models(LLMs) can reliably automate tourism-related prices when multiple, overlapping fare rules appl…
AFRIDOC-MT: Document-level MT Corpus for African Languages
Jesujoba O. Alabi, Israel Abebe Azime, Miaoran Zhang +13
This paper introduces AFRIDOC-MT, a document-level multi-parallel translation dataset covering English and five African languages: Amharic, Hausa, Swahili, Yorùbá, and Zulu. The da…
Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?
Dawei Zhu, Pinzhen Chen, Miaoran Zhang +3
Traditionally, success in multilingual machine translation can be attributed to three key factors in training data: large volume, diverse translation directions, and high quality.…
A Preference-driven Paradigm for Enhanced Translation with Large Language Models
Dawei Zhu, Sony Trenous, Xiaoyu Shen +3
Recent research has shown that large language models (LLMs) can achieve remarkable translation performance through supervised fine-tuning (SFT) using only a small amount of paralle…
Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?
Vagrant Gautam, Eileen Bingert, Dawei Zhu +2
Robust, faithful and harm-free pronoun use for individuals is an important goal for language model development as their use increases, but prior work tends to study only one or two…
LawBench: Benchmarking Legal Knowledge of Large Language Models
Zhiwei Fei, Xiaoyu Shen, Dawei Zhu +6
Large language models (LLMs) have demonstrated strong capabilities in various aspects. However, when applying them to the highly specialized, safe-critical legal domain, it is uncl…
Weaker Than You Think: A Critical Look at Weakly Supervised Learning
Dawei Zhu, Xiaoyu Shen, Marius Mosbach +2
Weakly supervised learning is a popular approach for training machine learning models in low-resource settings. Instead of requesting high-quality yet costly human annotations, it…
Task-Adaptive Pre-Training for Boosting Learning With Noisy Labels: A Study on Text Classification for African Languages
Dawei Zhu, Michael A. Hedderich, Fangzhou Zhai +2
For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many stan…
Meta Self-Refinement for Robust Learning with Weak Supervision
Dawei Zhu, Xiaoyu Shen, Michael A. Hedderich +1
Training deep neural networks (DNNs) under weak supervision has attracted increasing research attention as it can significantly reduce the annotation cost. However, labels from wea…
Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification
Dawei Zhu, Michael A. Hedderich, Fangzhou Zhai +2
Incorrect labels in training data occur when human annotators make mistakes or when the data is generated via weak or distant supervision. It has been shown that complex noise-hand…
Analysing the Noise Model Error for Realistic Noisy Label Data
Michael A. Hedderich, Dawei Zhu, Dietrich Klakow
Distant and weak supervision allow to obtain large amounts of labeled training data quickly and cheaply, but these automatic annotations tend to contain a high amount of errors. A…
Neural Data-to-Text Generation with LM-based Text Augmentation
Ernie Chang, Xiaoyu Shen, Dawei Zhu +2
For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instan…
Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages
Michael A. Hedderich, David Adelani, Dawei Zhu +3
Multilingual transformer models like mBERT and XLM-RoBERTa have obtained great improvements for many NLP tasks on a variety of languages. However, recent works also showed that res…
Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá
David Ifeoluwa Adelani, Michael A. Hedderich, Dawei Zhu +2
The lack of labeled training data has limited the development of natural language processing tools, such as named entity recognition, for many languages spoken in developing countr…
Image Manipulation with Natural Language using Two-sidedAttentive Conditional Generative Adversarial Network
Dawei Zhu, Aditya Mogadala, Dietrich Klakow
Altering the content of an image with photo editing tools is a tedious task for an inexperienced user. Especially, when modifying the visual attributes of a specific object in an i…