Related papers: If there's a Trigger Warning, then where's the Tri…
Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…
Programmers using bug-finding tools often review their reported warnings one by one. Based on the insight that identifying recurring themes and relationships can enhance the cognitive process of sensemaking, we propose CLARITY, which…
Text documents can be described by a number of abstract concepts such as semantic category, writing style, or sentiment. Machine learning (ML) models have been trained to automatically map documents to these abstract concepts, allowing to…
The proliferation of network-connected devices and applications has resulted in people receiving dozens, or hundreds, of notifications per day. When people are in the presence of others, each notification poses some risk of accidental…
The ability to accurately detect and filter offensive content automatically is important to ensure a rich and diverse digital discourse. Trolling is a type of hurtful or offensive content that is prevalent in social media, but is…
We present a novel class of jailbreak adversarial attacks on LLMs, termed Task-in-Prompt (TIP) attacks. Our approach embeds sequence-to-sequence tasks (e.g., cipher decoding, riddles, code execution) into the model's prompt to indirectly…
Annotation bias in NLP datasets remains a major challenge for developing multilingual Large Language Models (LLMs), particularly in culturally diverse settings. Bias from task framing, annotator subjectivity, and cultural mismatches can…
Static analysis tools are commonly used to detect defects before the code is released. Previous research has focused on their overall effectiveness and their ability to detect defects. However, little is known about the usage patterns of…
Classification is one of the most popular and widely used supervised learning tasks, which categorizes objects into predefined classes based on known knowledge. Classification has been an important research topic in machine learning and…
Programmers have long ignored warnings, especially those generated by static analysis tools, due to the potential for false-positives. In some cases, warnings may be indicative of larger issues, but programmers may not understand how a…
The amount of data for processing and categorization grows at an ever increasing rate. At the same time the demand for collaboration and transparency in organizations, government and businesses, drives the release of data from internal…
Neural text detectors are models trained to detect whether a given text was generated by a language model or written by a human. In this paper, we investigate three simple and resource-efficient strategies (parameter tweaking, prompt…
The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which…
Many NLP tasks require to automatically identify the most significant words in a text. In this work, we derive word significance from models trained to solve semantic task: Natural Language Inference and Paraphrase Identification. Using an…
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by…
In this work, we explore the constructive side of online reviews: advice, tips, requests, and suggestions that users provide about goods, venues, services, and other items of interest. To reduce training costs and annotation efforts needed…
We propose an annotation approach that captures not only labels but also the reading process underlying annotators' decisions, e.g., what parts of the text they focus on, re-read or skim. Using this framework, we conduct a case study on the…
Text annotation tools assume that their user's goal is to create a labeled corpus. However, users view annotation as a necessary evil on the way to deliver business value through NLP. Thus an annotation tool should optimize for the…
Recent advances in natural language processing (NLP) have contributed to the development of automated writing evaluation (AWE) systems that can correct grammatical errors. However, while these systems are effective at improving text, they…
Emotion recognition is predominantly formulated as text classification in which textual units are assigned to an emotion from a predefined inventory (e.g., fear, joy, anger, disgust, sadness, surprise, trust, anticipation). More recently,…