Despite the widespread adoption, there is a lack of research into how various critical aspects of pretrained language models (PLMs) affect their performance in hate speech detection. Through five research questions, our findings and recommendations lay the groundwork for empirically investigating different aspects of PLMs' use in hate speech detection. We deep dive into comparing different pretrained models, evaluating their seed robustness, finetuning settings, and the impact of pretraining data collection time. Our analysis reveals early peaks for downstream tasks during pretraining, the limited benefit of employing a more recent pretraining corpus, and the significance of specific layers during finetuning. We further call into question the use of domain-specific models and highlight the need for dynamic datasets for benchmarking hate speech detection.
* 20 pages, 9 figures, 14 tables. Accepted at EACL'24
In the evolving landscape of online communication, moderating hate speech (HS) presents an intricate challenge, compounded by the multimodal nature of digital content. This comprehensive survey delves into the recent strides in HS moderation, spotlighting the burgeoning role of large language models (LLMs) and large multimodal models (LMMs). Our exploration begins with a thorough analysis of current literature, revealing the nuanced interplay between textual, visual, and auditory elements in propagating HS. We uncover a notable trend towards integrating these modalities, primarily due to the complexity and subtlety with which HS is disseminated. A significant emphasis is placed on the advances facilitated by LLMs and LMMs, which have begun to redefine the boundaries of detection and moderation capabilities. We identify existing gaps in research, particularly in the context of underrepresented languages and cultures, and the need for solutions to handle low-resource settings. The survey concludes with a forward-looking perspective, outlining potential avenues for future research, including the exploration of novel AI methodologies, the ethical governance of AI in moderation, and the development of more nuanced, context-aware systems. This comprehensive overview aims to catalyze further research and foster a collaborative effort towards more sophisticated, responsible, and human-centric approaches to HS moderation in the digital era. WARNING: This paper contains offensive examples.
Code-mixing, the blending of multiple languages within a single conversation, introduces a distinctive challenge, particularly in the context of response generation. Capturing the intricacies of code-mixing proves to be a formidable task, given the wide-ranging variations influenced by individual speaking styles and cultural backgrounds. In this study, we explore response generation within code-mixed conversations. We introduce a novel approach centered on harnessing the Big Five personality traits acquired in an unsupervised manner from the conversations to bolster the performance of response generation. These inferred personality attributes are seamlessly woven into the fabric of the dialogue context, using a novel fusion mechanism, PA3. It uses an effective two-step attention formulation to fuse the dialogue and personality information. This fusion not only enhances the contextual relevance of generated responses but also elevates the overall performance of the model. Our experimental results, grounded in a dataset comprising of multi-party Hindi-English code-mix conversations, highlight the substantial advantages offered by personality-infused models over their conventional counterparts. This is evident in the increase observed in ROUGE and BLUE scores for the response generation task when the identified personality is seamlessly integrated into the dialogue context. Qualitative assessment for personality identification and response generation aligns well with our quantitative results.
Abstractive text summarization is surging with the number of training samples to cater to the needs of the deep learning models. These models tend to exploit the training data representations to attain superior performance by improving the quantitative element of the resultant summary. However, increasing the size of the training set may not always be the ideal solution to maximize the performance, and therefore, a need to revisit the quality of training samples and the learning protocol of deep learning models is a must. In this paper, we aim to discretize the vector space of the abstractive text summarization models to understand the characteristics learned between the input embedding space and the models' encoder space. We show that deep models fail to capture the diversity of the input space. Further, the distribution of data points on the encoder space indicates that an unchecked increase in the training samples does not add value; rather, a tear-down of data samples is highly needed to make the models focus on variability and faithfulness. We employ clustering techniques to learn the diversity of a model's sample space and how data points are mapped from the embedding space to the encoder space and vice versa. Further, we devise a metric to filter out redundant data points to make the model more robust and less data hungry. We benchmark our proposed method using quantitative metrics, such as Rouge, and qualitative metrics, such as BERTScore, FEQA and Pyramid score. We also quantify the reasons that inhibit the models from learning the diversity from the varied input samples.
Large Language Models (LLM) exhibit zero-shot mathematical reasoning capacity as a behavior emergent with scale, commonly manifesting as chain-of-thoughts (CoT) reasoning. However, multiple empirical findings suggest that this prowess is exclusive to LLMs with exorbitant sizes (beyond 50 billion parameters). Meanwhile, educational neuroscientists suggest that symbolic algebraic manipulation be introduced around the same time as arithmetic word problems to modularize language-to-formulation, symbolic manipulation of the formulation, and endgame arithmetic. In this paper, we start with the hypothesis that much smaller LMs, which are weak at multi-step reasoning, can achieve reasonable arithmetic reasoning if arithmetic word problems are posed as a formalize-then-solve task. In our architecture, which we call SYRELM, the LM serves the role of a translator to map natural language arithmetic questions into a formal language (FL) description. A symbolic solver then evaluates the FL expression to obtain the answer. A small frozen LM, equipped with an efficient low-rank adapter, is capable of generating FL expressions that incorporate natural language descriptions of the arithmetic problem (e.g., variable names and their purposes, formal expressions combining variables, etc.). We adopt policy-gradient reinforcement learning to train the adapted LM, informed by the non-differentiable symbolic solver. This marks a sharp departure from the recent development in tool-augmented LLMs, in which the external tools (e.g., calculator, Web search, etc.) are essentially detached from the learning phase of the LM. SYRELM shows massive improvements (e.g., +30.65 absolute point improvement in accuracy on the SVAMP dataset using GPT-J 6B model) over base LMs, while keeping our testbed easy to diagnose, interpret and within reach of most researchers.
In this work, we explore various topics that fall under the umbrella of Uncertainty in post-hoc Explainable AI (XAI) methods. We in particular focus on the class of additive feature attribution explanation methods. We first describe our specifications of uncertainty and compare various statistical and recent methods to quantify the same. Next, for a particular instance, we study the relationship between a feature's attribution and its uncertainty and observe little correlation. As a result, we propose a modification in the distribution from which perturbations are sampled in LIME-based algorithms such that the important features have minimal uncertainty without an increase in computational cost. Next, while studying how the uncertainty in explanations varies across the feature space of a classifier, we observe that a fraction of instances show near-zero uncertainty. We coin the term "stable instances" for such instances and diagnose factors that make an instance stable. Next, we study how an XAI algorithm's uncertainty varies with the size and complexity of the underlying model. We observe that the more complex the model, the more inherent uncertainty is exhibited by it. As a result, we propose a measure to quantify the relative complexity of a blackbox classifier. This could be incorporated, for example, in LIME-based algorithms' sampling densities, to help different explanation algorithms achieve tighter confidence levels. Together, the above measures would have a strong impact on making XAI models relatively trustworthy for the end-user as well as aiding scientific discovery.
As hate speech continues to proliferate on the web, it is becoming increasingly important to develop computational methods to mitigate it. Reactively, using black-box models to identify hateful content can perplex users as to why their posts were automatically flagged as hateful. On the other hand, proactive mitigation can be achieved by suggesting rephrasing before a post is made public. However, both mitigation techniques require information about which part of a post contains the hateful aspect, i.e., what spans within a text are responsible for conveying hate. Better detection of such spans can significantly reduce explicitly hateful content on the web. To further contribute to this research area, we organized HateNorm at HASOC-FIRE 2023, focusing on explicit span detection in English Tweets. A total of 12 teams participated in the competition, with the highest macro-F1 observed at 0.58.
A significant increase in content creation and information exchange has been made possible by the quick development of online social media platforms, which has been very advantageous. However, these platforms have also become a haven for those who disseminate false information, propaganda, and fake news. Claims are essential in forming our perceptions of the world, but sadly, they are frequently used to trick people by those who spread false information. To address this problem, social media giants employ content moderators to filter out fake news from the actual world. However, the sheer volume of information makes it difficult to identify fake news effectively. Therefore, it has become crucial to automatically identify social media posts that make such claims, check their veracity, and differentiate between credible and false claims. In response, we presented CLAIMSCAN in the 2023 Forum for Information Retrieval Evaluation (FIRE'2023). The primary objectives centered on two crucial tasks: Task A, determining whether a social media post constitutes a claim, and Task B, precisely identifying the words or phrases within the post that form the claim. Task A received 40 registrations, demonstrating a strong interest and engagement in this timely challenge. Meanwhile, Task B attracted participation from 28 teams, highlighting its significance in the digital era of misinformation.
With the proliferation of social media platforms, users are exposed to vast information, including posts containing misleading claims. However, the pervasive noise inherent in these posts presents a challenge in identifying precise and prominent claims that require verification. Extracting the core assertions from such posts is arduous and time-consuming. We introduce a novel task called Claim Normalization (aka ClaimNorm) that aims to decompose complex and noisy social media posts into more straightforward and understandable forms, termed normalized claims. We propose CACN, a pioneering approach that leverages chain-of-thought and claim check-worthiness estimation, mimicking human reasoning processes, to comprehend intricate claims. Moreover, we capitalize on large language models' powerful in-context learning abilities to provide guidance and improve the claim normalization process. To evaluate the effectiveness of our proposed model, we meticulously compile a comprehensive real-world dataset, CLAN, comprising more than 6k instances of social media posts alongside their respective normalized claims. Experimentation demonstrates that CACN outperforms several baselines across various evaluation measures. A rigorous error analysis validates CACN's capabilities and pitfalls.