Hate speech is a harmful form of online expression, often manifesting as derogatory posts. It is a significant risk in digital environments. With the rise of Large Language Models (LLMs), there is concern about their potential to replicate hate speech patterns, given their training on vast amounts of unmoderated internet data. Understanding how LLMs respond to hate speech is crucial for their responsible deployment. However, the behaviour of LLMs towards hate speech has been limited compared. This paper investigates the reactions of seven state-of-the-art LLMs (LLaMA 2, Vicuna, LLaMA 3, Mistral, GPT-3.5, GPT-4, and Gemini Pro) to hate speech. Through qualitative analysis, we aim to reveal the spectrum of responses these models produce, highlighting their capacity to handle hate speech inputs. We also discuss strategies to mitigate hate speech generation by LLMs, particularly through fine-tuning and guideline guardrailing. Finally, we explore the models' responses to hate speech framed in politically correct language.

This paper presents an Arabic Alphabet Sign Language recognition approach, using deep learning methods in conjunction with transfer learning and transformer-based models. We study the performance of the different variants on two publicly available datasets, namely ArSL2018 and AASL. This task will make full use of state-of-the-art CNN architectures like ResNet50, MobileNetV2, and EfficientNetB7, and the latest transformer models such as Google ViT and Microsoft Swin Transformer. These pre-trained models have been fine-tuned on the above datasets in an attempt to capture some unique features of Arabic sign language motions. Experimental results present evidence that the suggested methodology can receive a high recognition accuracy, by up to 99.6\% and 99.43\% on ArSL2018 and AASL, respectively. That is far beyond the previously reported state-of-the-art approaches. This performance opens up even more avenues for communication that may be more accessible to Arabic-speaking deaf and hard-of-hearing, and thus encourages an inclusive society.

In this paper we present a hybrid method for the automatic detection of dermatological pathologies in medical reports. We use a large language model combined with medical ontologies to predict, given a first appointment or follow-up medical report, the pathology a person may suffer from. The results show that teaching the model to learn the type, severity and location on the body of a dermatological pathology as well as in which order it has to learn these three features significantly increases its accuracy. The article presents the demonstration of state-of-the-art results for classification of medical texts with a precision of 0.84, micro and macro F1-score of 0.82 and 0.75, and makes both the method and the dataset used available to the community.

The impressive performance of proprietary LLMs like GPT4 in code generation has led to a trend to replicate these capabilities in open-source models through knowledge distillation (e.g. Code Evol-Instruct). However, these efforts often neglect the crucial aspect of response quality, relying heavily on teacher models for direct response distillation. This paradigm, especially for complex instructions, can degrade the quality of synthesized data, compromising the knowledge distillation process. To this end, our study introduces the Adaptive Modular Response Evolution (AMR-Evol) framework, which employs a two-stage process to refine response distillation. The first stage, modular decomposition, breaks down the direct response into more manageable sub-modules. The second stage, adaptive response evolution, automatically evolves the response with the related function modules. Our experiments with three popular code benchmarks (HumanEval, MBPP, and EvalPlus) attest to the superiority of the AMR-Evol framework over baseline response distillation methods. By comparing with the open-source Code LLMs trained on a similar scale of data, we observed performance enhancements: more than +3.0 points on HumanEval-Plus and +1.0 points on MBPP-Plus, which underscores the effectiveness of our framework. Our codes are available at https://github.com/ChiYeungLaw/AMR-Evol.

The rise of short-form videos on platforms like TikTok has brought new challenges in safeguarding young viewers from inappropriate content. Traditional moderation methods often fall short in handling the vast and rapidly changing landscape of user-generated videos, increasing the risk of children encountering harmful material. This paper introduces TikGuard, a transformer-based deep learning approach aimed at detecting and flagging content unsuitable for children on TikTok. By using a specially curated dataset, TikHarm, and leveraging advanced video classification techniques, TikGuard achieves an accuracy of 86.7%, showing a notable improvement over existing methods in similar contexts. While direct comparisons are limited by the uniqueness of the TikHarm dataset, TikGuard's performance highlights its potential in enhancing content moderation, contributing to a safer online experience for minors. This study underscores the effectiveness of transformer models in video classification and sets a foundation for future research in this area.

Code translation converts code from one programming language to another while maintaining its original functionality, which is crucial for software migration, system refactoring, and cross-platform development. Traditional rule-based methods rely on manually-written rules, which can be time-consuming and often result in less readable code. To overcome this, learning-based methods have been developed, leveraging parallel data to train models for automated code translation. More recently, the advance of Large Language Models (LLMs) further boosts learning-based code translation. Although promising, LLM-translated program still suffers from diverse quality issues (e.g., syntax errors and semantic errors). In particular, it can be challenging for LLMs to self-debug these errors when simply provided with the corresponding error messages. In this work, we propose a novel LLM-based multi-agent system TRANSAGENT, which enhances LLM-based code translation by fixing the syntax errors and semantic errors with the synergy between four LLM-based agents, including Initial Code Translator, Syntax Error Fixer, Code Aligner, and Semantic Error Fixer. The main insight of TRANSAGENT is to first localize the error code block in the target program based on the execution alignment between the target and source program, which can narrow down the fixing space and thus lower down the fixing difficulties. To evaluate TRANSAGENT, we first construct a new benchmark from recent programming tasks to mitigate the potential data leakage issue. On our benchmark, TRANSAGENT outperforms the latest LLM-based code translation technique UniTrans in both translation effectiveness and efficiency; additionally, our evaluation on different LLMs show the generalization of TRANSAGENT and our ablation study shows the contribution of each agent.

Recent advances in large language models (LLMs) have significantly impacted the domain of multi-hop question answering (MHQA), where systems are required to aggregate information and infer answers from disparate pieces of text. However, the autoregressive nature of LLMs inherently poses a challenge as errors may accumulate if mistakes are made in the intermediate reasoning steps. This paper introduces Monte-Carlo tree search for Zero-shot multi-hop Question Answering (MZQA), a framework based on Monte-Carlo tree search (MCTS) to identify optimal reasoning paths in MHQA tasks, mitigating the error propagation from sequential reasoning processes. Unlike previous works, we propose a zero-shot prompting method, which relies solely on instructions without the support of hand-crafted few-shot examples that typically require domain expertise. We also introduce a behavioral cloning approach (MZQA-BC) trained on self-generated MCTS inference trajectories, achieving an over 10-fold increase in reasoning speed with bare compromise in performance. The efficacy of our method is validated on standard benchmarks such as HotpotQA, 2WikiMultihopQA, and MuSiQue, demonstrating that it outperforms existing frameworks.

Sammy Selim strode through the dense, shiny green bushes on the slopes of his coffee farm in Sorwot village in Kericho, Kenya, accompanied by a younger farmer called Kennedy Kirui. They paused at each corner to input the farm's coordinates into a WhatsApp conversation. The conversation was with Virtual Agronomist, a tool that uses artificial intelligence to provide fertiliser application advice using chat prompts. The chatbot asked some further questions before producing a report saying that Selim should target a yield of 7.9 tonnes and use three types of fertiliser in specific quantities to achieve that goal. "My God!" Selim said upon receipt of the report.

In this work, we present AfriHuBERT, an extension of mHuBERT-147, a state-of-the-art (SOTA) and compact self-supervised learning (SSL) model, originally pretrained on 147 languages. While mHuBERT-147 was pretrained on 16 African languages, we expand this to cover 39 African languages through continued pretraining on 6,500+ hours of speech data aggregated from diverse sources, including 23 newly added languages. We evaluate AfriHuBERT on two key speech tasks: Language Identification (LID) and Automatic Speech Recognition (ASR) using FLEURS dataset. Our results show a +4% F1 score improvement on average for LID and a -1.2% average Word Error Rate (WER) reduction for ASR. Further analysis shows that ASR models trained on AfriHuBERT exhibit improved cross-corpus generalization. Additionally, the analysis indicates that the FLEURS have data quality limitations that may affect their suitability for evaluating low-resource African languages, suggesting the need for better evaluation benchmarks for these languages.

Explainable Artificial Intelligence (XAI) techniques are used to provide transparency to complex, opaque predictive models. However, these techniques are often designed for image and text data, and it is unclear how fit-for-purpose they are when applied to tabular data. As XAI techniques are rarely evaluated in settings with tabular data, the applicability of existing evaluation criteria and methods are also unclear and needs (re-)examination. For example, some works suggest that evaluation methods may unduly influence the evaluation results when using tabular data. This lack of clarity on evaluation procedures can lead to reduced transparency and ineffective use of XAI techniques in real world settings. In this study, we examine literature on XAI evaluation to derive guidelines on functionally-grounded assessment of local, post hoc XAI techniques. We identify 20 evaluation criteria and associated evaluation methods, and derive guidelines on when and how each criterion should be evaluated. We also identify key research gaps to be addressed by future work. Our study contributes to the body of knowledge on XAI evaluation through in-depth examination of functionally-grounded XAI evaluation protocols, and has laid the groundwork for future research on XAI evaluation.