Related papers: Random Silicon Sampling: Simulating Human Sub-Popu…
Chat-based large language models have the opportunity to empower individuals lacking high-quality healthcare access to receive personalized information across a variety of topics. However, users may ask underspecified questions that require…
Human groups are able to converge on more accurate beliefs through deliberation, even in the presence of polarization and partisan bias -- a phenomenon known as the "wisdom of partisan crowds." Generated agents powered by Large Language…
We propose a method for natural language generation, choosing the most representative output rather than the most likely output. By viewing the language generation process from the voting theory perspective, we define representativeness…
Beyond individual languages, multilingual natural language processing (NLP) research increasingly aims to develop models that perform well across languages generally. However, evaluating these systems on all the world's languages is…
Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to communicate in a natural manner. While techniques can…
Researchers have devised numerous ways to quantify social biases vested in pretrained language models. As some language models are capable of generating coherent completions given a set of textual prompts, several prompting datasets have…
Research has shown that while large language models (LLMs) can generate their responses based on cultural context, they are not perfect and tend to generalize across cultures. However, when evaluating the cultural bias of a language…
Large language models (LLMs) make it possible to generate synthetic behavioural data at scale, offering an ethical and low-cost alternative to human experiments. Whether such data can faithfully capture psychological differences driven by…
Self-supervised learning (SSL) speech models have achieved remarkable performance in various tasks, yet the biased outcomes, especially affecting marginalized groups, raise significant concerns. Social bias refers to the phenomenon where…
Large Language Models (LLMs) excel in text generation and understanding, especially in simulating socio-political and economic patterns, serving as an alternative to traditional surveys. However, their global applicability remains…
With the increasing capabilities of LLMs, recent studies focus on understanding whose opinions are represented by them and how to effectively extract aligned opinion distributions. We conducted an empirical analysis of three straightforward…
Question answering (Q/A) can be formulated as a generative task (Mitra, 2017) where the task is to generate an answer given the question and the passage (knowledge, if available). Recent advances in QA task is focused a lot on language…
The existence of juxtaposed regions of distinct cultures in spite of the fact that people's beliefs have a tendency to become more similar to each other's as the individuals interact repeatedly is a puzzling phenomenon in the social…
Opinion summarisation aims to summarise the salient information and opinions presented in documents such as product reviews, discussion forums, and social media texts into short summaries that enable users to effectively understand the…
Speech language models have significantly advanced in generating realistic speech, with neural codec language models standing out. However, the integration of human feedback to align speech outputs to human preferences is often neglected.…
A common limitation of diagnostic tests for detecting social biases in NLP models is that they may only detect stereotypic associations that are pre-specified by the designer of the test. Since enumerating all possible problematic…
Serendipity-oriented recommender systems aim to counteract over-specialization in user preferences. However, evaluating a user's serendipitous response towards a recommended item can be challenging because of its emotional nature. In this…
Considering the large amount of content created online by the minute, slang-aware automatic tools are critically needed to promote social good, and assist policymakers and moderators in restricting the spread of offensive language, abuse,…
We analyse a generalisation of the Galam model of binary opinion dynamics in which iterative discussions take place in local groups of individuals and study the effects of random deviations from the group majority. The probability of a…
Sociodemographic bias in language models (LMs) has the potential for harm when deployed in real-world settings. This paper presents a comprehensive survey of the past decade of research on sociodemographic bias in LMs, organized into a…