Gavin Abercrombie

Elisa Leonardelli, Alexandra Uma, Gavin Abercrombie et al.

NLP datasets annotated with human judgments are rife with disagreements between the judges. This is especially true for tasks depending on subjective judgments such as sentiment analysis or offensive language detection. Particularly in these latter cases, the NLP community has come to realize that the approach of 'reconciling' these different subjective interpretations is inappropriate. Many NLP researchers have therefore concluded that rather than eliminating disagreements from annotated corpora, we should preserve them-indeed, some argue that corpora should aim to preserve all annotator judgments. But this approach to corpus creation for NLP has not yet been widely accepted. The objective of the LeWiDi series of shared tasks is to promote this approach to developing NLP models by providing a unified framework for training and evaluating with such datasets. We report on the second LeWiDi shared task, which differs from the first edition in three crucial respects: (i) it focuses entirely on NLP, instead of both NLP and computer vision tasks in its first edition; (ii) it focuses on subjective tasks, instead of covering different types of disagreements-as training with aggregated labels for subjective NLP tasks is a particularly obvious misrepresentation of the data; and (iii) for the evaluation, we concentrate on soft approaches to evaluation. This second edition of LeWiDi attracted a wide array of participants resulting in 13 shared task submission papers.

Giulia Pucci, Emily Hemendinger, Ruizhe Li et al.

Recent evidence shows that people with eating disorders (EDs) are increasingly seeking guidance, advice, and emotional support from Large Language Model (LLM)-based chat systems. Although these systems are not designed to provide clinical advice, their perceived expertise, neutrality and accessibility make them a frequent, albeit risky, source of support. This paper investigates potential patterns of interaction between users with EDs and LLMs, focusing on the potential harms arising from models that uncritically adapt to, and facilitate unsafe or self-harming user requests. We find, in consultation with clinical ED experts, that specific linguistic cues in prompts increase the likelihood of unsafe responses and, through systematically varying the degree of potential risk present in the user prompt, report the extent to which LLMs uncritically adapt to problematic, and potentially dangerous user inputs.

Gavin Abercrombie, Tanvi Dinkar, Amanda Cercas Curry et al.

We commonly use agreement measures to assess the utility of judgements made by human annotators in Natural Language Processing (NLP) tasks. While inter-annotator agreement is frequently used as an indication of label reliability by measuring consistency between annotators, we argue for the additional use of intra-annotator agreement to measure label stability (and annotator consistency) over time. However, in a systematic review, we find that the latter is rarely reported in this field. Calculating these measures can act as important quality control and could provide insights into why annotators disagree. We conduct exploratory annotation experiments to investigate the relationships between these measures and perceptions of subjectivity and ambiguity in text items, finding that annotators provide inconsistent responses around 25% of the time across four different NLP tasks.

Yi-Ling Chung, Gavin Abercrombie, Florence Enock et al.

Counterspeech offers direct rebuttals to hateful speech by challenging perpetrators of hate and showing support to targets of abuse. It provides a promising alternative to more contentious measures, such as content moderation and deplatforming, by contributing a greater amount of positive online speech rather than attempting to mitigate harmful content through removal. Advances in the development of large language models mean that the process of producing counterspeech could be made more efficient by automating its generation, which would enable large-scale online campaigns. However, we currently lack a systematic understanding of several important factors relating to the efficacy of counterspeech for hate mitigation, such as which types of counterspeech are most effective, what are the optimal conditions for implementation, and which specific effects of hate it can best ameliorate. This paper aims to fill this gap by systematically reviewing counterspeech research in the social sciences and comparing methodologies and findings with computer science efforts in automatic counterspeech generation. By taking this multi-disciplinary view, we identify promising future directions in both fields.

Gavin Abercrombie, Verena Rieser

Conversational AI systems can engage in unsafe behaviour when handling users' medical queries that can have severe consequences and could even lead to deaths. Systems therefore need to be capable of both recognising the seriousness of medical inputs and producing responses with appropriate levels of risk. We create a corpus of human written English language medical queries and the responses of different types of systems. We label these with both crowdsourced and expert annotations. While individual crowdworkers may be unreliable at grading the seriousness of the prompts, their aggregated labels tend to agree with professional opinion to a greater extent on identifying the medical queries and recognising the risk types posed by the responses. Results of classification experiments suggest that, while these tasks can be automated, caution should be exercised, as errors can potentially be very serious.

Gavin Abercrombie, Djalel Benbouzid, Paolo Giudici et al.

This paper introduces a collaborative, human-centred taxonomy of AI, algorithmic and automation harms. We argue that existing taxonomies, while valuable, can be narrow, unclear, typically cater to practitioners and government, and often overlook the needs of the wider public. Drawing on existing taxonomies and a large repository of documented incidents, we propose a taxonomy that is clear and understandable to a broad set of audiences, as well as being flexible, extensible, and interoperable. Through iterative refinement with topic experts and crowdsourced annotation testing, we propose a taxonomy that can serve as a powerful tool for civil society organisations, educators, policymakers, product teams and the general public. By fostering a greater understanding of the real-world harms of AI and related technologies, we aim to increase understanding, empower NGOs and individuals to identify and report violations, inform policy discussions, and encourage responsible technology development and deployment.

Tanvi Dinkar, Aiqi Jiang, Gavin Abercrombie et al.

Social media has exacerbated the promotion of Western beauty norms, leading to negative self-image, particularly in women and girls, and causing harm such as body dysmorphia. Increasingly content on the internet has been artificially generated, leading to concerns that these norms are being exaggerated. The aim of this work is to study how generative AI models may encode 'beauty' and erase 'ugliness', and discuss the implications of this for society. To investigate these aims, we create two image generation pipelines: a text-to-image model and a text-to-language model-to image model. We develop a structured beauty taxonomy which we use to prompt three language models (LMs) and two text-to-image models to cumulatively generate 5984 images using our two pipelines. We then recruit women and non-binary social media users to evaluate 1200 of the images through a Likert-scale within-subjects study. Participants show high agreement in their ratings. Our results show that 86.5% of generated images depicted people with lighter skin tones, 22% contained explicit content despite Safe for Work (SFW) training, and 74% were rated as being in a younger age demographic. In particular, the images of non-binary individuals were rated as both younger and more hypersexualised, indicating troubling intersectional effects. Notably, prompts encoded with 'negative' or 'ugly' beauty traits (such as "a wide nose") consistently produced higher Not SFW (NSFW) ratings regardless of gender. This work sheds light on the pervasive demographic biases related to beauty standards present in generative AI models -- biases that are actively perpetuated by model developers, such as via negative prompting. We conclude by discussing the implications of this on society, which include pollution of the data streams and active erasure of features that do not fall inside the stereotype of what is considered beautiful by developers.

Flor Miriam Plaza-del-Arco, Amanda Cercas Curry, Alba Curry et al.

Large language models (LLMs) reflect societal norms and biases, especially about gender. While societal biases and stereotypes have been extensively researched in various NLP applications, there is a surprising gap for emotion analysis. However, emotion and gender are closely linked in societal discourse. E.g., women are often thought of as more empathetic, while men's anger is more socially accepted. To fill this gap, we present the first comprehensive study of gendered emotion attribution in five state-of-the-art LLMs (open- and closed-source). We investigate whether emotions are gendered, and whether these variations are based on societal stereotypes. We prompt the models to adopt a gendered persona and attribute emotions to an event like 'When I had a serious argument with a dear person'. We then analyze the emotions generated by the models in relation to the gender-event pairs. We find that all models consistently exhibit gendered emotions, influenced by gender stereotypes. These findings are in line with established research in psychology and gender studies. Our study sheds light on the complex societal interplay between language, gender, and emotion. The reproduction of emotion stereotypes in LLMs allows us to use those models to study the topic in detail, but raises questions about the predictive use of those same LLMs for emotion applications.

Helena Bonaldi, Yi-Ling Chung, Gavin Abercrombie et al.

In recent years, counterspeech has emerged as one of the most promising strategies to fight online hate. These non-escalatory responses tackle online abuse while preserving the freedom of speech of the users, and can have a tangible impact in reducing online and offline violence. Recently, there has been growing interest from the Natural Language Processing (NLP) community in addressing the challenges of analysing, collecting, classifying, and automatically generating counterspeech, to reduce the huge burden of manually producing it. In particular, researchers have taken different directions in addressing these challenges, thus providing a variety of related tasks and resources. In this paper, we provide a guide for doing research on counterspeech, by describing - with detailed examples - the steps to undertake, and providing best practices that can be learnt from the NLP studies on this topic. Finally, we discuss open challenges and future directions of counterspeech research in NLP.

Amanda Cercas Curry, Gavin Abercrombie, Zeerak Talat

Natural language processing research has begun to embrace the notion of annotator subjectivity, motivated by variations in labelling. This approach understands each annotator's view as valid, which can be highly suitable for tasks that embed subjectivity, e.g., sentiment analysis. However, this construction may be inappropriate for tasks such as hate speech detection, as it affords equal validity to all positions on e.g., sexism or racism. We argue that the conflation of hate and offence can invalidate findings on hate speech, and call for future work to be situated in theory, disentangling hate from its orthogonal concept, offence.

Tanvi Dinkar, Aiqi Jiang, Simona Frenda et al.

Counterspeech, i.e. the practice of responding to online hate speech, has gained traction in NLP as a promising intervention. While early work emphasised collaboration with non-governmental organisation stakeholders, recent research trends have shifted toward automated pipelines that reuse a small set of legacy datasets, often without input from affected communities. This paper presents a systematic review of 74 NLP studies on counterspeech, analysing the extent to which stakeholder participation influences dataset creation, model development, and evaluation. To complement this analysis, we conducted a participatory case study with five NGOs specialising in online Gender-Based Violence (oGBV), identifying stakeholder-informed practices for counterspeech generation. Our findings reveal a growing disconnect between current NLP research and the needs of communities most impacted by toxic online content. We conclude with concrete recommendations for re-centring stakeholder expertise in counterspeech research.

Gavin Abercrombie, Amanda Cercas Curry, Tanvi Dinkar et al.

Automated dialogue or conversational systems are anthropomorphised by developers and personified by users. While a degree of anthropomorphism may be inevitable due to the choice of medium, conscious and unconscious design choices can guide users to personify such systems to varying degrees. Encouraging users to relate to automated systems as if they were human can lead to high risk scenarios caused by over-reliance on their outputs. As a result, natural language processing researchers have investigated the factors that induce personification and develop resources to mitigate such effects. However, these efforts are fragmented, and many aspects of anthropomorphism have yet to be explored. In this paper, we discuss the linguistic factors that contribute to the anthropomorphism of dialogue systems and the harms that can arise, including reinforcing gender stereotypes and notions of acceptable language. We recommend that future efforts towards developing dialogue systems take particular care in their design, development, release, and description; and attend to the many linguistic cues that can elicit personification by users.

Fatma Elsafoury, Gavin Abercrombie

In this paper, we trace the biases in current natural language processing (NLP) models back to their origins in racism, sexism, and homophobia over the last 500 years. We review literature from critical race theory, gender studies, data ethics, and digital humanities studies, and summarize the origins of bias in NLP models from these social science perspective. We show how the causes of the biases in the NLP pipeline are rooted in social issues. Finally, we argue that the only way to fix the bias and unfairness in NLP is by addressing the social problems that caused them in the first place and by incorporating social sciences and social scientists in efforts to mitigate bias in NLP models. We provide actionable recommendations for the NLP research community to do so.

Nikolas Vitsakis, Amit Parekh, Tanvi Dinkar et al.

There are two competing approaches for modelling annotator disagreement: distributional soft-labelling approaches (which aim to capture the level of disagreement) or modelling perspectives of individual annotators or groups thereof. We adapt a multi-task architecture -- which has previously shown success in modelling perspectives -- to evaluate its performance on the SEMEVAL Task 11. We do so by combining both approaches, i.e. predicting individual annotator perspectives as an interim step towards predicting annotator disagreement. Despite its previous success, we found that a multi-task approach performed poorly on datasets which contained distinct annotator opinions, suggesting that this approach may not always be suitable when modelling perspectives. Furthermore, our results explain that while strongly perspectivist approaches might not achieve state-of-the-art performance according to evaluation metrics used by distributional approaches, our approach allows for a more nuanced understanding of individual perspectives present in the data. We argue that perspectivist approaches are preferable because they enable decision makers to amplify minority views, and that it is important to re-evaluate metrics to reflect this goal.

Anya Belz, Craig Thomson, Ehud Reiter et al.

We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining what makes human evaluations in NLP more/less reproducible. We present our results and findings, which include that just 13\% of papers had (i) sufficiently low barriers to reproduction, and (ii) enough obtainable information, to be considered for reproduction, and that all but one of the experiments we selected for reproduction was discovered to have flaws that made the meaningfulness of conducting a reproduction questionable. As a result, we had to change our coordinated study design from a reproduce approach to a standardise-then-reproduce-twice approach. Our overall (negative) finding that the great majority of human evaluations in NLP is not repeatable and/or not reproducible and/or too flawed to justify reproduction, paints a dire picture, but presents an opportunity for a rethink about how to design and report human evaluations in NLP.

Amanda Cercas Curry, Gavin Abercrombie, Verena Rieser

We present the first English corpus study on abusive language towards three conversational AI systems gathered "in the wild": an open-domain social bot, a rule-based chatbot, and a task-based system. To account for the complexity of the task, we take a more `nuanced' approach where our ConvAI dataset reflects fine-grained notions of abuse, as well as views from multiple expert annotators. We find that the distribution of abuse is vastly different compared to other commonly used datasets, with more sexually tinted aggression towards the virtual persona of these systems. Finally, we report results from bench-marking existing models against this data. Unsurprisingly, we find that there is substantial room for improvement with F1 scores below 90%.

Emily Dinan, Gavin Abercrombie, A. Stevie Bergman et al.

Over the last several years, end-to-end neural conversational agents have vastly improved in their ability to carry a chit-chat conversation with humans. However, these models are often trained on large datasets from the internet, and as a result, may learn undesirable behaviors from this data, such as toxic or otherwise harmful language. Researchers must thus wrestle with the issue of how and when to release these models. In this paper, we survey the problem landscape for safety for end-to-end conversational AI and discuss recent and related work. We highlight tensions between values, potential positive impact and potential harms, and provide a framework for making decisions about whether and how to release these models, following the tenets of value-sensitive design. We additionally provide a suite of tools to enable researchers to make better-informed decisions about training and releasing end-to-end conversational AI models.

Gavin Abercrombie, Amanda Cercas Curry, Mugdha Pandya et al.

Technology companies have produced varied responses to concerns about the effects of the design of their conversational AI systems. Some have claimed that their voice assistants are in fact not gendered or human-like -- despite design features suggesting the contrary. We compare these claims to user perceptions by analysing the pronouns they use when referring to AI assistants. We also examine systems' responses and the extent to which they generate output which is gendered and anthropomorphic. We find that, while some companies appear to be addressing the ethical concerns raised, in some cases, their claims do not seem to hold true. In particular, our results show that system outputs are ambiguous as to the humanness of the systems, and that users tend to personify and gender them as a result.

Gavin Abercrombie, Riza Batista-Navarro

Parliamentary and legislative debate transcripts provide access to information concerning the opinions, positions and policy preferences of elected politicians. They attract attention from researchers from a wide variety of backgrounds, from political and social sciences to computer science. As a result, the problem of automatic sentiment and position-taking analysis has been tackled from different perspectives, using varying approaches and methods, and with relatively little collaboration or cross-pollination of ideas. The existing research is scattered across publications from various fields and venues. In this article we present the results of a systematic literature review of 61 studies, all of which address the automatic analysis of the sentiment and opinions expressed and positions taken by speakers in parliamentary (and other legislative) debates. In this review, we discuss the available research with regard to the aims and objectives of the researchers who work on these problems, the automatic analysis tasks they undertake, and the approaches and methods they use. We conclude by summarizing their findings, discussing the challenges of applying computational analysis to parliamentary debates, and suggesting possible avenues for further research.