Training large language models (LLMs) with open-domain instruction data has yielded remarkable success in aligning to end tasks and user preferences. Extensive research has highlighted that enhancing the quality and diversity of instruction data consistently improves performance. However, the impact of data complexity, as a crucial metric, remains relatively unexplored in three aspects: (1) scaling law, where the sustainability of performance improvements with increasing complexity is uncertain, (2) additional tokens, whether the improvement brought by complexity comes from introducing more training tokens, and (3) curriculum tuning, where the potential advantages of incorporating instructions ranging from easy to difficult are not yet fully understood. In this paper, we propose \textit{tree-instruct} to systematically enhance the complexity of instruction data in a controllable manner. This approach adds a specified number of nodes into the instruction semantic tree, yielding new instruction data based on the modified tree. By adjusting the number of added nodes, we can control the difficulty level in the modified instruction data. Our preliminary experiments reveal the following insights: (1) Increasing complexity consistently leads to sustained performance improvements. For instance, using 1,000 instruction data and 10 nodes resulted in a substantial 24\% increase in win rate. (2) Under the same token budget, a few complex instructions outperform diverse yet simple instructions. (3) Curriculum instruction tuning might not yield the anticipated results; focusing on increasing complexity appears to be the key.

The task of retrieving already debunked narratives aims to detect stories that have already been fact-checked. The successful detection of claims that have already been debunked not only reduces the manual efforts of professional fact-checkers but can also contribute to slowing the spread of misinformation. Mainly due to the lack of readily available data, this is an understudied problem, particularly when considering the cross-lingual task, i.e. the retrieval of fact-checking articles in a language different from the language of the online post being checked. This paper fills this gap by (i) creating a novel dataset to enable research on cross-lingual retrieval of already debunked narratives, using tweets as queries to a database of fact-checking articles; (ii) presenting an extensive experiment to benchmark fine-tuned and off-the-shelf multilingual pre-trained Transformer models for this task; and (iii) proposing a novel multistage framework that divides this cross-lingual debunk retrieval task into refinement and re-ranking stages. Results show that the task of cross-lingual retrieval of already debunked narratives is challenging and off-the-shelf Transformer models fail to outperform a strong lexical-based baseline (BM25). Nevertheless, our multistage retrieval framework is robust, outperforming BM25 in most scenarios and enabling cross-domain and zero-shot learning, without significantly harming the model's performance.

The spread of toxic content online is an important problem that has adverse effects on user experience online and in our society at large. Motivated by the importance and impact of the problem, research focuses on developing solutions to detect toxic content, usually leveraging machine learning (ML) models trained on human-annotated datasets. While these efforts are important, these models usually do not generalize well and they can not cope with new trends (e.g., the emergence of new toxic terms). Currently, we are witnessing a shift in the approach to tackling societal issues online, particularly leveraging large language models (LLMs) like GPT-3 or T5 that are trained on vast corpora and have strong generalizability. In this work, we investigate how we can use LLMs and prompt learning to tackle the problem of toxic content, particularly focusing on three tasks; 1) Toxicity Classification, 2) Toxic Span Detection, and 3) Detoxification. We perform an extensive evaluation over five model architectures and eight datasets demonstrating that LLMs with prompt learning can achieve similar or even better performance compared to models trained on these specific tasks. We find that prompt learning achieves around 10\% improvement in the toxicity classification task compared to the baselines, while for the toxic span detection task we find better performance to the best baseline (0.643 vs. 0.640 in terms of $F_1$-score). Finally, for the detoxification task, we find that prompt learning can successfully reduce the average toxicity score (from 0.775 to 0.213) while preserving semantic meaning.

The Reinforcement Learning from Human Feedback (RLHF) plays a pivotal role in shaping the impact of large language models (LLMs), contributing significantly to controlling output toxicity and selecting output styles, particularly as LLMs often harbor misleading content, highlighting the urgency to align them with human values for secure AI systems. The RLHF, characterized by complexity, instability, and sensitivity to hyperparameters, makes the evaluation of the reward model for complex tasks challenging, thereby further complicating the use of Proximal Policy Optimization (PPO). In this paper, we introduce a simple task designed to employ Gloden as a reward model that validates the effectiveness of PPO and inspires it, primarily explaining the task of utilizing PPO to manipulate the tokenizer length of the output generated by the model. Experiments confirm that PPO is not only effective in manipulating the output tokenizer length to a certain extent in this type of task but also exhibits facilitated training once the influence of the reward model effect is excluded, making it an exciting development.

Large language models (LLMs), such as ChatGPT, have demonstrated outstanding performance in various fields, particularly in natural language understanding and generation tasks. In complex application scenarios, users tend to engage in multi-turn conversations with ChatGPT to keep contextual information and obtain comprehensive responses. However, human forgetting and model contextual forgetting remain prominent issues in multi-turn conversation scenarios, which challenge the users' conversation comprehension and contextual continuity for ChatGPT. To address these challenges, we propose an interactive conversation visualization system called C5, which includes Global View, Topic View, and Context-associated Q\&A View. The Global View uses the GitLog diagram metaphor to represent the conversation structure, presenting the trend of conversation evolution and supporting the exploration of locally salient features. The Topic View is designed to display all the question and answer nodes and their relationships within a topic using the structure of a knowledge graph, thereby display the relevance and evolution of conversations. The Context-associated Q\&A View consists of three linked views, which allow users to explore individual conversations deeply while providing specific contextual information when posing questions. The usefulness and effectiveness of C5 were evaluated through a case study and a user study.

Transformer-based language models (TLMs) have widely been recognized to be a cutting-edge technology for the successful development of deep-learning-based solutions to problems and applications that require natural language processing and understanding. Like for other textual domains, TLMs have indeed pushed the state-of-the-art of AI approaches for many tasks of interest in the legal domain. Despite the first Transformer model being proposed about six years ago, there has been a rapid progress of this technology at an unprecedented rate, whereby BERT and related models represent a major reference, also in the legal domain. This article provides the first systematic overview of TLM-based methods for AI-driven problems and tasks in the legal sphere. A major goal is to highlight research advances in this field so as to understand, on the one hand, how the Transformers have contributed to the success of AI in supporting legal processes, and on the other hand, what are the current limitations and opportunities for further research development.

Deceptive text classification is a critical task in natural language processing that aims to identify deceptive o fraudulent content. This study presents a comparative analysis of machine learning and transformer-based approaches for deceptive text classification. We investigate the effectiveness of traditional machine learning algorithms and state-of-the-art transformer models, such as BERT, XLNET, DistilBERT, and RoBERTa, in detecting deceptive text. A labeled dataset consisting of deceptive and non-deceptive texts is used for training and evaluation purposes. Through extensive experimentation, we compare the performance metrics, including accuracy, precision, recall, and F1 score, of the different approaches. The results of this study shed light on the strengths and limitations of machine learning and transformer-based methods for deceptive text classification, enabling researchers and practitioners to make informed decisions when dealing with deceptive content.

Trust in AI agents has been extensively studied in the literature, resulting in significant advancements in our understanding of this field. However, the rapid advancements in Large Language Models (LLMs) and the emergence of LLM-based AI agent frameworks pose new challenges and opportunities for further research. In the field of process automation, a new generation of AI-based agents has emerged, enabling the execution of complex tasks. At the same time, the process of building automation has become more accessible to business users via user-friendly no-code tools and training mechanisms. This paper explores these new challenges and opportunities, analyzes the main aspects of trust in AI agents discussed in existing literature, and identifies specific considerations and challenges relevant to this new generation of automation agents. We also evaluate how nascent products in this category address these considerations. Finally, we highlight several challenges that the research community should address in this evolving landscape.

Ensuring alignment, which refers to making models behave in accordance with human intentions [1,2], has become a critical task before deploying large language models (LLMs) in real-world applications. For instance, OpenAI devoted six months to iteratively aligning GPT-4 before its release [3]. However, a major challenge faced by practitioners is the lack of clear guidance on evaluating whether LLM outputs align with social norms, values, and regulations. This obstacle hinders systematic iteration and deployment of LLMs. To address this issue, this paper presents a comprehensive survey of key dimensions that are crucial to consider when assessing LLM trustworthiness. The survey covers seven major categories of LLM trustworthiness: reliability, safety, fairness, resistance to misuse, explainability and reasoning, adherence to social norms, and robustness. Each major category is further divided into several sub-categories, resulting in a total of 29 sub-categories. Additionally, a subset of 8 sub-categories is selected for further investigation, where corresponding measurement studies are designed and conducted on several widely-used LLMs. The measurement results indicate that, in general, more aligned models tend to perform better in terms of overall trustworthiness. However, the effectiveness of alignment varies across the different trustworthiness categories considered. This highlights the importance of conducting more fine-grained analyses, testing, and making continuous improvements on LLM alignment. By shedding light on these key dimensions of LLM trustworthiness, this paper aims to provide valuable insights and guidance to practitioners in the field. Understanding and addressing these concerns will be crucial in achieving reliable and ethically sound deployment of LLMs in various applications.

Online violence against children has increased globally recently, demanding urgent attention. Competent authorities manually analyze abuse complaints to comprehend crime dynamics and identify patterns. However, the manual analysis of these complaints presents a challenge because it exposes analysts to harmful content during the review process. Given these challenges, we present a novel solution, an automated tool designed to analyze children's sexual abuse reports comprehensively. By automating the analysis process, our tool significantly reduces the risk of exposure to harmful content by categorizing the reports on three dimensions: Subject, Degree of Criminality, and Damage. Furthermore, leveraging our multidisciplinary team's expertise, we introduce a novel approach to annotate the collected data, enabling a more in-depth analysis of the reports. This approach improves the comprehension of fundamental patterns and trends, enabling law enforcement agencies and policymakers to create focused strategies in the fight against children's violence.