Related papers: ToxiTrace: Gradient-Aligned Training for Explainab…
Considerable effort has been dedicated to mitigating toxicity, but existing methods often require drastic modifications to model parameters or the use of computationally intensive auxiliary models. Furthermore, previous approaches have…
Recent AI agents, such as ChatGPT and LLaMA, primarily rely on instruction tuning and reinforcement learning to calibrate the output of large language models (LLMs) with human intentions, ensuring the outputs are harmless and helpful.…
We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and (2) use of paraphrasing models…
In an era of rapidly evolving internet technology, the surge in multimodal content, including videos, has expanded the horizons of online communication. However, the detection of toxic content in this diverse landscape, particularly in…
Knowledge Graphs~(KGs) often suffer from unreliable knowledge, which restricts their utility. Triple Classification~(TC) aims to determine the validity of triples from KGs. Recently, text-based methods learn entity and relation…
Recently, tampered text detection has attracted increasing attention due to its essential role in information security. Although existing methods can detect the tampered text region, the interpretation of such detection remains unclear,…
In recent years, the widespread use of social media has led to an increase in the generation of toxic and offensive content on online platforms. In response, social media platforms have worked on developing automatic detection methods and…
Emotion stimulus detection is the task of finding the cause of an emotion in a textual description, similar to target or aspect detection for sentiment analysis. Previous work approached this in three ways, namely (1) as text classification…
Scene text recognition has been studied for decades due to its broad applications. However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few…
This system report presents our approaches and results for the Chinese Essay Fluency Evaluation (CEFE) task at CCL-2024. For Track 1, we optimized predictions for challenging fine-grained error types using binary classification models and…
Algorithmic bias often arises as a result of differential subgroup validity, in which predictive relationships vary across groups. For example, in toxic language detection, comments targeting different demographic groups can vary markedly…
Text-to-Table aims to generate structured tables to convey the key information from unstructured documents. Existing text-to-table datasets are typically oriented English, limiting the research in non-English languages. Meanwhile, the…
During the development of large language models (LLMs), the scale and quality of the pre-training data play a crucial role in shaping LLMs' capabilities. To accelerate the research of LLMs, several large-scale datasets, such as C4 [1], Pile…
Although semi-supervised learning has made significant advances in the field of medical image segmentation, fully annotating a volumetric sample slice by slice remains a costly and time-consuming task. Even worse, most of the existing…
The goal of semantic role labeling (SRL) is to discover the predicate-argument structure of a sentence, which plays a critical role in deep processing of natural language. This paper introduces simple yet effective auxiliary tags for…
The accuracy of prosodic structure prediction is crucial to the naturalness of synthesized speech in Mandarin text-to-speech system, but now is limited by widely-used sequence-to-sequence framework and error accumulation from previous word…
Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most…
Citation faithfulness detection is critical for enhancing retrieval-augmented generation (RAG) systems, yet large-scale Chinese datasets for this task are scarce. Existing methods face prohibitive costs due to the need for manually…
Each and every organisation releases information in a variety of forms ranging from annual reports to legal proceedings. Such documents may contain sensitive information and releasing them openly may lead to the leakage of confidential…
Large Language Models (LLMs), such as ChatGPT and GPT-4, have dramatically transformed natural language processing research and shown promising strides towards Artificial General Intelligence (AGI). Nonetheless, the high costs associated…