Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech Generation

Gupta, Rajiv; Desai, Shaily; Goel, Manmohan Dass; Bandhakavi, Anil; Chakraborty, Tanmoy; Akhtar, Md. Shad

doi:10.18653/v1/2023.acl-long.318

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study participants described many different barriers to counterspeech at various stages of engagement as discussed in Section 4.1. However, previous works in AI have focused on a narrow set of challenges for assistance and automation: automatic counterspeech generation [53,55,108,149] and analysis and detection of both hate speech and counterspeech [43,63]. Our findings paint a broader picture, especially through the theory of counterspeech engagement, and highlight where tools and resources would encourage bystander intervention towards countering hate.…”

Section: Possible Tools To Address Barriers To Counterspeechmentioning

confidence: 78%

“…Prior works on automatic generation of counterspeech [91,149] relied on curated or scraped datasets [25,63] and evaluation metrics based on correct countering claims [55] or emotion and politeness [108]. Some methods used limited response intent such as question, denouncing, and humor in dataset [25] and as part of the generation method [53]. In addition, counterspeech generation in dialogue systems (e.g., Alexa, Cortana, etc.)…”

Section: Ai Assistance In Counterspeechmentioning

confidence: 99%

See 1 more Smart Citation

Counterspeakers’ Perspectives: Unveiling Barriers and AI Needs in the Fight against Online Hate

Mun,

Buerger,

Liang

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Counterspeech, i.e., direct responses against hate speech, has become an important tool to address the increasing amount of hate online while avoiding censorship. Although AI has been proposed to help scale up counterspeech efforts, this raises questions of how exactly AI could assist in this process, since counterspeech is a deeply empathetic and agentic process for those involved. In this work, we aim to answer this question, by conducting in-depth interviews with 10 extensively experienced counterspeakers and a large scale public survey with 342 everyday social media users. In participant responses, we identified four main types of barriers and AI needs related to resources, training, impact, and personal harms. However, our results also revealed overarching concerns of authenticity, agency, and functionality in using AI tools for counterspeech. To conclude, we discuss considerations for designing AI assistants that lower counterspeaking barriers without jeopardizing its meaning and purpose. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI.

show abstract

Section: Possible Tools To Address Barriers To Counterspeechmentioning

confidence: 78%

Section: Ai Assistance In Counterspeechmentioning

confidence: 99%

Counterspeakers’ Perspectives: Unveiling Barriers and AI Needs in the Fight against Online Hate

Mun,

Buerger,

Liang

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Despite the limitations of n-gram-overlap metrics, they are still widely used to evaluate counterspeech (Gupta et al, 2023). But, faced with the shortcomings of these metrics, some authors have conducted manual evaluations for automatically generated counter-narratives, in line with the methods of the Natural Language generation community (Shimorina and Belz, 2022).…”

Section: Evaluation Methods For Generated Counter-narrativesmentioning

confidence: 99%

High-quality argumentative information in low resources approaches improve counter-narrative generation

Furman,

Torres,

Rodríguez

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

It has been shown that high quality fine-tuning boosts the performance of language models, even if the size of the fine-tuning is small. In this work we show how highly targeted fine-tuning improves the task of hate speech counter-narrative generation in user-generated text, even for very small sizes of training (1722 counter-narratives for English and 355 for Spanish). Providing a small subset of examples focusing on single argumentative strategies, together with the argumentative analysis relevant to that strategy, yields counter-narratives that are as satisfactory as providing the whole set of counter-narratives. We also show that a good base model is required for the fine-tuning to have a positive impact. Indeed, for Spanish, the counter-narratives obtained without fine-tuning are mostly unacceptable, and, while fine-tuning improves their overall quality, the performance still remains quite unsatisfactory.

show abstract

“…Despite the vast and apt interest in computational methods for hate speech detection, issues with generalizable [65] and biasing [21] are prevalent and active areas of research. Further sister tasks that employ LLMs for proactive mitigation [33], counter-speech generation [23,44] and implicit explanation [47,52] underpinned by hate speech detection have also been proposed. Especially within the area of unearthing the context of implicit hate speech, some studies explored leveraging external context in the form of either knowledge-graph tuples [18] or Wikipedia summaries [30].…”

Section: Related Workmentioning

confidence: 99%

Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalization

Masud

Bedi

Khan

et al. 2022

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Although pre-trained large language models (PLMs) have achieved state-of-the-art on many NLP tasks, they lack understanding of subtle expressions of implicit hate speech. Such nuanced and implicit hate is often misclassified as non-hate. Various attempts have been made to enhance the detection of (implicit) hate content by augmenting external context or enforcing label separation via distance-based metrics. We combine these two approaches and introduce FiADD, a novel Focused Inferential Adaptive Density Discrimination framework. FiADD enhances the PLM finetuning pipeline by bringing the surface form of an implicit hate speech closer to its implied form while increasing the inter-cluster distance among various class labels. We test FiADD on three implicit hate datasets and observe significant improvement in the two-way and three-way hate classification tasks. We further experiment on the generalizability of FiADD on three other tasks, namely detecting sarcasm, irony, and stance, in which surface and implied forms differ, and observe similar performance improvement. We analyze the generated latent space to understand its evolution under FiADD, which corroborates the advantage of employing FiADD for implicit hate speech detection. 1

show abstract

Counterspeeches up my sleeve! Intent Distribution Learning and Persistent Fusion for Intent-Conditioned Counterspeech Generation

Cited by 4 publications

References 0 publications

Counterspeakers’ Perspectives: Unveiling Barriers and AI Needs in the Fight against Online Hate

Counterspeakers’ Perspectives: Unveiling Barriers and AI Needs in the Fight against Online Hate

High-quality argumentative information in low resources approaches improve counter-narrative generation

Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalization

Contact Info

Product

Resources

About