19 accepted papers
Fine‑tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EMA): Even a small, domain‑specific fine‑tune can induce harmful behaviors far outside the target domain. Even in the case where model weights are hidden behi…
Pluralism, the capacity to engage with diverse perspectives without collapsing them into a single viewpoint, is critical for developing large language models that faithfully reflect human heterogeneity. Yet this characteristic has not been carefully examined within the LLM research community and rem…
Large language models (LLMs) often generate hallucinated content, making it crucial to identify and quantify inconsistencies in their outputs. We introduce HaluMap, a post-hoc framework that detects hallucinations by mapping entailment and contradiction relations between source inputs and generated…
Hyperbolic representations are effective in modeling knowledge graph data which is prevalently used to facilitate multi-hop reasoning. However, a rigorous and detailed comparison of the two spaces for this task is lacking. In this paper, through a simple integration of hyperbolic representations wit…
Conceptual operationalizations of empathy in NLP are varied, with some having specific behaviors and properties, while others are more abstract. How these variations relate to one another and capture properties of empathy observable in text remains unclear. To provide insight into this, we analyze t
Analyzing user opinion changes in long conversation threads is extremely critical for applications like enhanced personalization, market research, political campaigns, customer service, targeted advertising, and content moderation. Unfortunately, previous studies on stance and dogmatism in user conv…
Empathy is essential in healthcare communication. We introduce an annotation approach that draws on well-established frameworks for clinical empathy and breaking bad news (BBN) conversations for considering the interactive dynamics of discourse relations. We construct Empathy in BBNs, a span-relatio…
Recent trends in natural language processing research and annotation tasks affirm a paradigm shift from the traditional reliance on a single ground truth to a focus on individual perspectives, particularly in subjective tasks. In scenarios where annotation tasks are meant to encompass diversity, mod…
In today’s rapidly evolving digital age, disinformation poses a significant threat to public sentiment and socio-political dynamics. To address this, we introduce a new dataset “DeFaktS”, designed to understand and counter disinformation within German media. Distinctively curated across various news…
Empathetic leadership communication plays a pivotal role in modern workplaces as it is associated with a wide range of positive individual and organizational outcomes. This paper introduces LeadEmpathy, an innovative expert-annotated German dataset for modeling empathy in written leadership communic…
Although language model performance across diverse tasks continues to improve, these models still struggle to understand and explain the beliefs of other people. This skill requires perspective-taking, the process of conceptualizing the point of view of another person. Perspective taking becomes cha…
The performance cost of differential privacy has, for some applications, been shown to be higher for minority groups; fairness, conversely, has been shown to disproportionally compromise the privacy of members of such groups. Most work in this area has been restricted to computer vision and risk ass…
We review the state of research on empathy in natural language processing and identify the following issues: (1) empathy definitions are absent or abstract, which (2) leads to low construct validity and reproducibility. Moreover, (3) emotional empathy is overemphasized, skewing our focus to a narrow…
Interpolation-based regularisation methods such as Mixup, which generate virtual training samples, have proven to be effective for various tasks and modalities. We extend Mixup and propose DMix, an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embed…
Large pre-trained neural language models have supported the effectiveness of many NLP tasks, yet are still prone to generating toxic language hindering the safety of their use. Using empathetic data, we improve over recent work on controllable text generation that aims to reduce the toxicity of gene…
Instead of using a single ground truth for language processing tasks, several recent studies have examined how to represent and predict the labels of the set of annotators. However, often little or no information about annotators is known, or the set of annotators is small. In this work, we examine…
Interpolation-based regularisation methods for data augmentation have proven to be effective for various tasks and modalities. These methods involve performing mathematical operations over the raw input samples or their latent states representations - vectors that often possess complex hierarchical…
Existing sarcasm detection systems focus on exploiting linguistic markers, context, or user-level priors. However, social studies suggest that the relationship between the author and the audience can be equally relevant for the sarcasm usage and interpretation. In this work, we propose a framework j…
Recent psychological studies indicate that individuals exhibiting suicidal ideation increasingly turn to social media rather than mental health practitioners. Personally contextualizing the buildup of such ideation is critical for accurate identification of users at risk. In this work, we propose a…