Related papers: COBRA Frames: Contextual Reasoning about Effects a…
Healthcare data often come from multiple sites in which the correlations between confounding variables can vary widely. If deep learning models exploit these unstable correlations, they might fail catastrophically in unseen sites. Although…
Value trade-offs are an integral part of human decision-making and language use, however, current tools for interpreting such dynamic and multi-faceted notions of values in language models are limited. In cognitive science, so-called…
People's social relationships are often manifested through their surroundings, with certain objects or interactions acting as symbols for specific relationships, e.g., wedding rings, roses, hugs, or holding hands. This brings unique…
This paper conducts a user study to assess whether three machine learning (ML) interpretability layouts can influence participants' views when evaluating sentences containing hate speech, focusing on the "Misogyny" and "Racism" classes.…
Sarcasm can be defined as saying or writing the opposite of what one truly wants to express, usually to insult, irritate, or amuse someone. Because of the obscure nature of sarcasm in textual data, detecting it is difficult and of great…
Offensive speech detection is a key component of content moderation. However, what is offensive can be highly subjective. This paper investigates how machine and human moderators disagree on what is offensive when it comes to real-world…
While various approaches have recently been studied for bias identification, little is known about how implicit language that does not explicitly convey a viewpoint affects bias amplification in large language models. To examine the…
Large Language Models (LLMs) have significantly advanced natural language processing applications, yet their widespread use raises concerns regarding inherent biases that may reduce utility or harm for particular social groups. Despite the…
The prevalence of offensive content on the internet, encompassing hate speech and cyberbullying, is a pervasive issue worldwide. Consequently, it has garnered significant attention from the machine learning (ML) and natural language…
Memes, which rapidly disseminate personal opinions and positions across the internet, also pose significant challenges in propagating social bias and prejudice. This study presents a novel approach to detecting harmful memes, particularly…
Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of LLMs encompasses various…
Predicting affect in unconstrained environments remains a fundamental challenge in human-centered AI. While deep neural embeddings dominate contemporary approaches, they often lack interpretability and limit expert-driven refinement. We…
Large language models often suffer from language confusion, a phenomenon in which responses are partially or entirely generated in unintended languages. This critically degrades the user experience, especially in low-resource settings. We…
Natural language inference (NLI) is a fundamental NLP task, investigating the entailment relationship between two texts. Popular NLI datasets present the task at sentence-level. While adequate for testing semantic representations, they fall…
Hate speech is a challenging issue plaguing the online social media. While better models for hate speech detection are continuously being developed, there is little research on the bias and interpretability aspects of hate speech. In this…
Manipulation tasks require robots to reason about cause and effect when interacting with objects. Yet, many data-driven approaches lack causal semantics and thus only consider correlations. We introduce COBRA-PPM, a novel causal Bayesian…
Warning: this paper contains content that maybe offensive or upsetting. Recent research in Natural Language Processing (NLP) has advanced the development of various toxicity detection models with the intention of identifying and mitigating…
Contextual automatic speech recognition (ASR) with Speech-LLMs is typically trained with oracle conversation history, but relies on error-prone history at inference, causing a train-test mismatch in the context channel that we term…
Biased news contributes to societal polarization and is often reinforced by hostile reader comments, constituting a vital yet often overlooked aspect of news dissemination. Our study reveals that offensive comments support biased content,…
The substantial growth of online learning, in particular, Massively Open Online Courses (MOOCs), supports research into the development of better models for effective learning. Learner 'confusion' is among one of the identified aspects…