相关论文: Manipulation of Perceived Politeness in a Web-base…

Ad hominem attacks are those that target some feature of a person's character instead of the position the person is maintaining. These attacks are harmful because they propagate implicit biases and diminish a person's credibility. Since…

Human communication is fundamentally creative, and often makes use of subtext -- implied meaning that goes beyond the literal content of the text. Here, we systematically study whether language models can use subtext in communicative…

There are many contexts in which dyadic data are present. Social networks are a well-known example. In these contexts, pairs of elements are linked building a network that reflects interactions. Explaining why these relationships are…

Computational approach to politeness is the task of automatically predicting and generating politeness in text. This is a pivotal task for conversational analysis, given the ubiquity and challenges of politeness in interactions. The…

Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their reliance on dynamic web content, however, makes them vulnerable to prompt injection attacks:…

Multi-agent debate (MAD) frameworks have emerged as promising approaches for misinformation detection by simulating adversarial reasoning. While prior work has focused on detection accuracy, it overlooks the importance of helping users…

Unbiased data collection is essential to guaranteeing fairness in artificial intelligence models. Implicit bias, a form of behavioral conditioning that leads us to attribute predetermined characteristics to members of certain groups and…

Backdoor attacks on text classifiers can cause them to predict a predefined label when a particular "trigger" is present. Prior attacks often rely on triggers that are ungrammatical or otherwise unusual, leading to conspicuous attacks. As a…

The recent text-to-speech (TTS) has achieved quality comparable to that of humans; however, its application in spoken dialogue has not been widely studied. This study aims to realize a TTS that closely resembles human dialogue. First, we…

In recent years, agents have become capable of communicating seamlessly via natural language and navigating in environments that involve cooperation and competition, a fact that can introduce social dilemmas. Due to the interleaving of…

Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human…

The increasing sophistication of large language models (LLMs) has sparked growing concerns regarding their potential role in exacerbating ideological polarization through the automated generation of persuasive and biased content. This study…

As AI-enabled systems become available for political campaign outreach, an important question has received little empirical attention: how do people evaluate the communicative practices these systems represent, and what consequences do…

This paper focuses on simulating text dialogues in which impressions between speakers improve during speed dating. This simulation involves selecting an utterance from multiple candidates generated by a text generation model that replicates…

Background: Deception detection through analysing language is a promising avenue using both human judgments and automated machine learning judgments. For both forms of credibility assessment, automated adversarial attacks that rewrite…

Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" in "leet speak"), among other scenarios. We consider this as a new type of adversarial attack in NLP,…

Anonymity in social media platforms keeps users hidden behind a keyboard. This absolves users of responsibility, allowing them to engage in online rage, hate speech, and other text-based toxicity that harms online well-being. Recent…

Textual deception constitutes a major problem for online security. Many studies have argued that deceptiveness leaves traces in writing style, which could be detected using text classification techniques. By conducting an extensive…

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Agents powered by large language models (LLMs) are increasingly deployed in settings where communication shapes high-stakes decisions, making a principled understanding of strategic communication essential. Prior work largely studies either…